Search

Machine learning (ML) algorithms were recently adapted for testing integrated circuits and detecting potential design backdoors. Such testing mechanisms mainly rely on the available training dataset and the extracted features of the Trojan circuit. In this letter, we demonstrate that this method is attackable by exploiting a structural problem of classifiers for hardware Trojan (HT) detection in gate-level netlists, called the boundary net (BN) problem. There, an adversary modifies the labels of those BNs, connecting the original logic to the Trojan circuit. We show that the proposed adversarial label-flipping attacks (ALFAs) are potentially highly toxic to the accuracy of supervised ML-based Trojan detection approaches. The experimental results indicate that an adversary needs to flip only 0.09% of all labels to achieve an accuracy drop of over 9%, demonstrating one of the most efficient ALFAs in the HT detection research domain. [ABSTRACT FROM AUTHOR]

Emotional arousal, an essential dimension of game users’ experience, plays a crucial role in determining whether a game is successful. Game users’ emotion arousal assessment (GUEA) is of great importance. However, GUEA often faces challenges, such as selecting emotion-inducing games, labeling emotional arousal, and improving accuracy. In this study, the scheme for verifying the effectiveness of emotion-induced games is proposed so that the selected games can induce the target emotions. In addition, the personalized arousal label generation method is developed to reduce the errors caused by individual differences among subjects. Furthermore, to improve the accuracy of GUEA, the Breath Rate Variability (BRV) signal is used as a GUEA indicator along with commonly used physiological signals. Comparative experiments on GUEA based on multimodal physiological signals are conducted. The experimental result shows that the accuracy of GUEA is improved by adding the BRV signal, up to 92%. [ABSTRACT FROM AUTHOR]

Emotion recognition is a key attribute for artificial intelligence systems that need to naturally interact with humans. However, the task definition is still an open problem due to the inherent ambiguity of emotions. In this paper, a novel Bayesian training loss based on per-utterance Dirichlet prior distributions is proposed for verbal emotion recognition, which models the uncertainty in one-hot labels created when human annotators assign the same utterance to different emotion classes. An additional metric is used to evaluate the performance by detecting test utterances with high labelling uncertainty. This removes a major limitation that emotion classification systems only consider utterances with labels where the majority of annotators agree on the emotion class. Furthermore, a frequentist approach is studied to leverage the continuous-valued “soft” labels obtained by averaging the one-hot labels. We propose a two-branch model structure for emotion classification on a per-utterance basis, which achieves state-of-the-art classification results on the widely used IEMOCAP dataset. Based on this, uncertainty estimation experiments were performed. The best performance in terms of the area under the precision-recall curve when detecting utterances with high uncertainty was achieved by interpolating the Bayesian training loss with the Kullback-Leibler divergence training loss for the soft labels. The generality of the proposed approach was verified using the MSP-Podcast dataset which yielded the same pattern of results. [ABSTRACT FROM AUTHOR]

Most person re-identification methods, being supervised techniques, suffer from the burden of massive annotation requirement. Unsupervised methods overcome this need for labeled data, but perform poorly compared to the supervised alternatives. In order to cope with this issue, we introduce the problem of learning person re-identification models from videos with weak supervision. The weak nature of the supervision arises from the requirement of video-level labels, i.e. person identities who appear in the video, in contrast to the more precise frame-level annotations. Towards this goal, we propose a multiple instance attention learning framework for person re-identification using such video-level labels. Specifically, we first cast the video person re-identification task into a multiple instance learning setting, in which person images in a video are collected into a bag. The relations between videos with similar labels can be utilized to identify persons, on top of that, we introduce a co-person attention mechanism which mines the similarity correlations between videos with person identities in common. The attention weights are obtained based on all person images instead of person tracklets in a video, making our learned model less affected by noisy annotations. Extensive experiments demonstrate the superiority of the proposed method over the related methods on two weakly labeled person re-identification datasets.

Data quality plays an important role during the training stage of machine/deep learning models. The annotation hinges on the experiences of domain experts. To acquire the expert’s knowledge in the context of machine learning, manual data labeling, a tedious and time-consuming task in supervised learning, should be given a top priority. However, the domain experts in the line of plentiful manual annotation may easily get distracted or fatigued after long-time work, causing judgment errors, mislabeling, etc. The pattern recognition of wafer defect map is investigated in this paper, the primary goal of which is to train the convolutional neural network (CNN) model through a very limited number of manually labeled data so that the trained model is capable of performing pseudo labeling. Subsequently, a self-assured adaptive ensemble learner in terms of a series of shallow neural networks is proposed to filter wafer map samples with untrusted pseudo-labels. In the result, the amount of human annotations is significantly reduced by 61% for training a highly accurate classifier. A minimum number of manually labeled data is suggested while the equally high classification performance of wafer defect pattern is maintained. For the evaluation purpose, the proposed self-assured learning is compared with the confidence learning. [ABSTRACT FROM AUTHOR]

There is growing interest in affective computing for the representation and prediction of emotions along ordinal scales. However, the term ordinal emotion label has been used to refer to both absolute notions such as low or high arousal, as well as relation notions such as arousal is higher at one instance compared to another. In this paper, we introduce the terminology absolute and relative ordinal labels to make this distinction clear and investigate both with a view to integrate them and exploit their complementary nature. We propose a Markovian framework referred to as Dynamic Ordinal Markov Model (DOMM) that makes use of both absolute and relative ordinal information, to improve speech based ordinal emotion prediction. Finally, the proposed framework is validated on two speech corpora commonly used in affective computing, the RECOLA and the IEMOCAP databases, across a range of system configurations. The results consistently indicate that integrating relative ordinal information improves absolute ordinal emotion prediction. [ABSTRACT FROM AUTHOR]

In this letter, we introduce deep active learning (AL) for multi-label image classification (MLC) problems in remote sensing (RS). In particular, we investigate the effectiveness of several AL query functions for the MLC of RS images. Unlike the existing AL query functions (which are defined for single-label classification or semantic segmentation problems), each query function in this letter is based on the evaluation of two criteria: 1) multi-label uncertainty and 2) multi-label diversity. The multi-label uncertainty criterion is associated with the confidence of the deep neural networks (DNNs) in correctly assigning multi-labels to each image. To assess this criterion, we investigate three strategies: 1) learning multi-label loss ordering; 2) measuring temporal discrepancy of multi-label predictions; and 3) measuring the magnitude of approximated gradient embeddings. The multi-label diversity criterion is associated with the selection of a set of images that are as diverse as possible to each other which prevents redundancy among them. To assess this criterion, we exploit a clustering-based strategy. We combine each of the abovementioned uncertainty strategies with the clustering-based diversity strategy, resulting in three different query functions. All the considered query functions are introduced for the first time in the framework of MLC problems in RS. Experimental results obtained on two benchmark archives show that these query functions result in the selection of a highly informative set of samples at each iteration of the AL process. [ABSTRACT FROM AUTHOR]

Insufficient prior knowledge of a captured hyperspectral image (HSI) scene may lead the experts or the automatic labeling systems to offer incorrect labels or ambiguous labels (i.e., assigning each training sample to a group of candidate labels, among which only one of them is valid; this is also known as partial label learning) during the labeling process. Accordingly, how to learn from such data with ambiguous labels is a problem of great practical importance. In this letter, we propose a novel superpixelwise low-rank approximation (LRA)-based partial label learning method, namely SLAP, which is the first to take into account partial label learning in HSI classification. SLAP is mainly composed of two phases: disambiguating the training labels and acquiring the predictive model. Specifically, in the first phase, we propose a superpixelwise LRA-based model, preparing the affinity graph for the subsequent label propagation process while extracting the discriminative representation to enhance the following classification task of the second phase. Then to disambiguate the training labels, label propagation propagates the labeling information via the affinity graph of training pixels. In the second phase, we take advantage of the resulting disambiguated training labels and the discriminative representations to enhance the classification performance. The extensive experiments validate the advantage of the proposed SLAP method over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning is being increasingly employed for hyperspectral classification, although such use is often predicated on the availability of a sufficiently large set of labeled samples for training. To improve classification performance under a limited training-set size, a semi-supervised network with end-to-end local–global active learning (AL) based on graph convolutional networks (GCNs) is proposed. The proposed AL extracts both global as well as local graph-based features to gauge the discriminative information in unlabeled samples, while semi-supervised classification expands the training set of a fully supervised classifier by attaching pseudo-labels to high-confidence unlabeled samples. Experimental results demonstrate that the proposed network outperforms not only other approaches to semi-supervised classification but also several existing fully supervised methods. The source code of this method can be found at https://github.com/XtaoS/semi-LG-AGCN. [ABSTRACT FROM AUTHOR]

Variations in perspective, illumination, motion blur, and weatherworn degeneration of signs may all be essential factors in road-sign identification. The current research purpose is to evaluate the effectiveness of the image processing technique in detecting road signs as well as to find the appropriate threshold value range for doing so. The efficiency of the cascade object detector in detecting road signs was tested under variations of speed and threshold values. The suggested system involved using video data to calculate the number of frames per second and creating an output file that contains the specified targets with their labels to use later in the final process (i.e., training stage). In the current research, two videos captured some types of traffic signs (40, 60, 80, and cross signs) in Palestine and Al-Rubaie streets during night time in Baghdad city. The practical significance is demonstrated here by using the optimal threshold value for more accurate object detection. Through an increase in threshold values, results show that the highest precision value, which is equal to one, occurred for crossroad sign relations with stable behavior, followed by 80 (i.e., 1-0.824) and 60-speed signs (i.e., 1-0.315), respectively, with positive relationships, and ended by speed sign 40, which witnessed a reverse relationship with increasing threshold values until the breakdown case took place, which usually occurred above the threshold value equal to thirty (i.e., 0.471-0.134). [ABSTRACT FROM AUTHOR]

This community service aims to carry out a business assistance program for women's groups at the Munyai Mekhawan Business Savings Cooperative (KSU), Pesisir Barat District, Lampung Province. The community service program is carried out through a mentoring method that will be held by the Faculty of Economics, Sang Bumi Ruwa Jurai University, with the target of KSU members Munyai Mekhawan Labuhan Mandi. The contribution given is in the form of making herbal medicines for women's herbal processing business groups (Spices) in the form of packaging and labeling training activities. The results of these activities indicate that the implementation of the training received a positive response and high enthusiasm from the KSU Muway Mekhawan group because of the increased knowledge possessed by the business group, and has the potential to be developed and become additional household income. Based on the activities that have been carried out, the servant hopes that there will be other community service programs that can increase people's income through household businesses.

Human gait phase estimation has been studied in the field of robotics due to its importance in controlling wearable devices (e.g., robotic prostheses or exoskeletons) in a synchronized manner with the user. Researchers have attempted to estimate the user’s gait phase using a learning-based method, as data-driven approaches have recently emerged in the field. In this study, we propose a new labeling method (i.e., a piecewise linear label) to have the estimator learn the ground truth based on variable toe-off onset at different walking speeds. Using whole-body marker data, we computed the angular positions and velocities of thigh and torso segments and utilized them as input data for model training. Three models (i.e., general, slow, and normal-fast) were obtained based on long short-term memory (LSTM). These models are compared in order to identify the effect of the piecewise linear label at various walking speeds. As a result, when the proposed labeling method was used while training the general model, the estimation accuracy was significantly improved. This fact was also found when estimating the user’s gait phase during the mid-stance phase. Furthermore, the proposed method maintained good performance in detecting the heel-strike and toe-off. According to the findings of this study, the newly proposed labeling method could improve speed-adaptability in gait phase estimation, resulting in outstanding accuracy for both gait phase, heel-strike, and toe-off estimation. [ABSTRACT FROM AUTHOR]

In partial label learning, a multi-class classifier is learned from the ambiguous supervision where each training example is associated with a set of candidate labels among which only one is valid. An intuitive way to deal with this problem is label disambiguation, i.e., differentiating the labeling confidences of different candidate labels so as to try to recover ground-truth labeling information. Recently, feature-aware label disambiguation has been proposed which utilizes the graph structure of feature space to generate labeling confidences over candidate labels. Nevertheless, the existence of noises and outliers in training data makes the graph structure derived from original feature space less reliable. In this paper, a novel partial label learning approach based on adaptive graph guided disambiguation is proposed, which is shown to be more effective in revealing the intrinsic manifold structure among training examples. Other than the sequential disambiguation-then-induction learning strategy, the proposed approach jointly performs adaptive graph construction, candidate label disambiguation and predictive model induction with alternating optimization. Furthermore, we consider the particular human-in-the-loop framework in which a learner is allowed to actively query some ambiguously labeled examples for manual disambiguation. Extensive experiments clearly validate the effectiveness of adaptive graph guided disambiguation for learning from partial label examples. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation crowd counting (UDACC) has been studied with practical research utility by getting rid of the labeling burden on large-scale dense crowds in the target domain. Current methods generalize well within the specific domain gap by directly aligning domain distributions or translating synthetic data to realistic images. However, it is difficult to define domain gaps among complex real-world datasets, in which the images vary greatly in style, density level and/or content. To tackle this problem, in this paper, we propose a Cross-Domain Attention Network (CDANet), which can effectively generalize the model to the unlabeled domain on both unsupervised synthetic-to-realistic and realistic-to-realistic crowd counting. Specifically, we propose a Cross-Domain Attention Module (CDAM) to learn domain-related information between the source and target domain, which extracts relations in cross-domain attentive information, thus enhancing crowd-informative features. Moreover, to make our CDAM invariant to domain shifts, we introduce a consistency penalty to ensure that the attention maps are consistent before and after the domain shifting. Thus our CDANet can pay attention to the shared counting information across domains, while remaining its invariant ability during domain adaptation. Extensive experiments on several common benchmarks for UDACC demonstrate that our CDANet gets competitive results on both unsupervised synthetic-to-realistic and realistic-to-realistic UDACC tasks. [ABSTRACT FROM AUTHOR]

In conventional person re-identification (re-id), the images used for model training in the training probe set and training gallery set are all assumed to be instance-level samples that are manually labeled from raw surveillance video (likely with the assistance of detection) in a frame-by-frame manner. This labeling across multiple non-overlapping camera views from raw video surveillance is expensive and time consuming. To overcome these issues, we consider a weakly supervised person re-id modeling that aims to find the raw video clips where a given target person appears. In our weakly supervised setting, during training, given a sample of a person captured in one camera view, our weakly supervised approach aims to train a re-id model without further instance-level labeling for this person in another camera view. The weak setting refers to matching a target person with an untrimmed gallery video where we only know that the identity appears in the video without the requirement of annotating the identity in any frame of the video during the training procedure. The weakly supervised person re-id is challenging since it not only suffers from the difficulties occurring in conventional person re-id (e.g., visual ambiguity and appearance variations caused by occlusions, pose variations, background clutter, etc.), but more importantly, is also challenged by weakly supervised information because the instance-level labels and the ground-truth locations for person instances (i.e., the ground-truth bounding boxes of person instances) are absent. To solve the weakly supervised person re-id problem, we develop deep graph metric learning (DGML). On the one hand, DGML measures the consistency between intra-video spatial graphs of consecutive frames, where the spatial graph captures neighborhood relationship about the detected person instances in each frame. On the other hand, DGML distinguishes the inter-video spatial graphs captured from different camera views at different sites simultaneously. To further explicitly embed weak supervision into the DGML and solve the weakly supervised person re-id problem, we introduce weakly supervised regularization (WSR), which utilizes multiple weak video-level labels to learn discriminative features by means of a weak identity loss and a cross-video alignment loss. We conduct extensive experiments to demonstrate the feasibility of the weakly supervised person re-id approach and its special cases (e.g., its bag-to-bag extension) and show that the proposed DGML is effective. [ABSTRACT FROM AUTHOR]

We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet. [ABSTRACT FROM AUTHOR]

Few-shot learning under the $N$ N -way $K$ K -shot setting (i.e., $K$ K annotated samples for each of $N$ N classes) has been widely studied in relation extraction (e.g., FewRel) and image classification (e.g., Mini-ImageNet). Named entity recognition (NER) is typically framed as a sequence labeling problem where the entity classes are inherently entangled together because the entity number and classes in a sentence are not known in advance, leaving the $N$ N -way $K$ K -shot NER problem so far unexplored. In this paper, we first formally define a more suitable $N$ N -way $K$ K -shot setting for NER. Then we propose FewNER, a novel meta-learning approach for few-shot NER. FewNER separates the entire network into a task-independent part and a task-specific part. During training in FewNER, the task-independent part is meta-learned across multiple tasks and the task-specific part is learned for each individual task in a low-dimensional space. At test time, FewNER keeps the task-independent part fixed and adapts to a new task via gradient descent by updating only the task-specific part, resulting in it being less prone to overfitting and more computationally efficient. Compared with pre-trained language models (e.g., BERT and ELMo) which obtain the transferability in an implicit manner (i.e., relying on large-scale corpora), FewNER explicitly optimizes the capability of “learning to adapt quickly” through meta-learning. The results demonstrate that FewNER achieves state-of-the-art performance against nine baseline methods by significant margins on three adaptation experiments (i.e., intra-domain cross-type, cross-domain intra-type and cross-domain cross-type). [ABSTRACT FROM AUTHOR]

The success of zero-shot action recognition (ZSAR) methods is intrinsically related to the nature of semantic side information used to transfer knowledge, although this aspect has not been primarily investigated in the literature. This work introduces a new ZSAR method based on the relationships of actions-objects and actions-descriptive sentences. We demonstrate that representing all object classes using descriptive sentences generates an accurate object-action affinity estimation when a paraphrase estimation method is used as an embedder. We also show how to estimate probabilities over the set of action classes based only on a set of sentences without hard human labeling. In our method, the probabilities from these two global classifiers (i.e., which use features computed over the entire video) are combined, producing an efficient transfer knowledge model for action classification. Our results are state-of-the-art in the Kinetics-400 dataset and are competitive on UCF-101 under the ZSAR evaluation. Our code is available at https://github.com/valterlej/objsentzsar. [ABSTRACT FROM AUTHOR]

This paper studies instance-dependent Positive and Unlabeled (PU) classification, where whether a positive example will be labeled (indicated by $s$ s ) is not only related to the class label $y$ y , but also depends on the observation $\mathbf {x}$ x . Therefore, the labeling probability on positive examples is not uniform as previous works assumed, but is biased to some simple or critical data points. To depict the above dependency relationship, a graphical model is built in this paper which further leads to a maximization problem on the induced likelihood function regarding $P(s,y|\mathbf {x})$ P (s , y | x) . By utilizing the well-known EM and Adam optimization techniques, the labeling probability of any positive example $P(s=1|y=1,\mathbf {x})$ P (s = 1 | y = 1 , x) as well as the classifier induced by $P(y|\mathbf {x})$ P (y | x) can be acquired. Theoretically, we prove that the critical solution always exists, and is locally unique for linear model if some sufficient conditions are met. Moreover, we upper bound the generalization error for both linear logistic and non-linear network instantiations of our algorithm, with the convergence rate of expected risk to empirical risk as $\mathcal {O}(1/\sqrt{k}+1/\sqrt{n-k}+1/\sqrt{n})$ O (1 / k + 1 / n - k + 1 / n) ($k$ k and $n$ n are the sizes of positive set and the entire training set, respectively). Empirically, we compare our method with state-of-the-art instance-independent and instance-dependent PU algorithms on a wide range of synthetic, benchmark and real-world datasets, and the experimental results firmly demonstrate the advantage of the proposed method over the existing PU approaches. [ABSTRACT FROM AUTHOR]

Data-driven fault detection has been regarded as a 3-D image segmentation task. The models trained from synthetic data are difficult to generalize in some surveys. Recently, training 3-D fault segmentation using sparse manual 2-D slices is thought to yield promising results, but manual labeling has many false negative labels (FNLs) (abnormal annotations), which is detrimental to training and consequently to detection performance. Motivated to train 3-D fault segmentation networks under sparse 2-D labels while suppressing FNLs, we analyze the training process gradient and propose the mask dice (MD) loss. Moreover, the fault is an edge feature, and current encoder–decoder architectures widely used for fault detection (e.g., U-shape network) are not conducive to edge representation. Consequently, fault-net is proposed, which is designed for the characteristics of faults, employs high-resolution propagation features, and embeds multiscale compression fusion block to fuse multiscale information, which allows the edge information to be fully preserved during propagation and fusion, thus enabling advanced performance via few computational resources. The experiment demonstrates that MD loss supports the inclusion of human experience in training and suppresses FNLs therein, enabling baseline models to improve performance and generalize to more surveys. Fault-Net is capable of providing a more stable and reliable interpretation of faults, and it uses extremely low computational resources and inference is significantly faster than other models. Our method indicates optimal performance in comparison with several mainstream methods. [ABSTRACT FROM AUTHOR]

Applications challenged by the joint problem of concept drift and class imbalance are attracting increasing research interest. This paper proposes a novel Reinforcement Online Active Learning Ensemble for Drifting Imbalanced data stream (ROALE-DI). The ensemble classifier has a long-term stable classifier and a dynamic classifier group which applies a reinforcement mechanism to increase the weight of the dynamic classifiers, which perform better on the minority class, and decreases the weight of the opposite. When the data stream is class imbalanced, the classifiers will lack the training samples of the minority class. To supply training samples, when creating a new classifier, the labeled instances buffer is used to provide instances of the minority class. Then, a hybrid labeling strategy that combines the uncertainty strategy and imbalance strategy is proposed to define whether to obtain the real label of an instance. An experimental evaluation compares the classification performance of the proposed method with semi-supervised and supervised algorithms on both real-world and synthetic data streams. The results show that the ROALE-DI achieves higher Area Under the ROC Curve (AUC) and accuracy values with even fewer real labels, and the labeling cost dynamically adjusts according to the concept drift and class imbalance ratio. [ABSTRACT FROM AUTHOR]

Partial multi-label learning (PML) deals with problems where each instance is assigned with a candidate label set, which contains multiple relevant labels and some noisy labels. Recent studies usually solve PML problems with the disambiguation strategy, which recovers ground-truth labels from the candidate label set by simply assuming that the noisy labels are generated randomly. In real applications, however, noisy labels are usually caused by some ambiguous contents of the example. Based on this observation, we propose a partial multi-label learning approach to simultaneously recover the ground-truth information and identify the noisy labels. The two objectives are formalized in a unified framework with trace norm and $\ell _1$ ℓ 1 norm regularizers. Under the supervision of the observed noise-corrupted label matrix, the multi-label classifier and noisy label identifier are jointly optimized by incorporating the label correlation exploitation and feature-induced noise model. Furthermore, by mapping each bag to a feature vector, we extend PML-NI method into multi-instance multi-label learning by identifying noisy labels based on ambiguous instances. A theoretical analysis of generalization bound and extensive experiments on multiple data sets from various real-world tasks demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Label-efficient scene segmentation aims to achieve effective per-pixel classification with reduced labeling effort. Recent approaches for this task focus on leveraging unlabelled images by formulating consistency regularization or pseudo labels for individual pixels. Yet most of these methods ignore the 3D geometric structures naturally conveyed by image scenes, which is free for enhancing training segmentation models with better discrimination of image details. In this work, we present a novel Geometric Structure Refinement (GSR) framework to explicitly exploit the geometric structures of image scenes to enhance the semi-supervised training of segmentation models. In the training phase, we generate initial dense pseudo labels based on fast and coarse annotations, and then utilize the free unsupervised 3D reconstruction of the image scene to calibrate the dense pseudo labels with more reliable details. With the calibrated pseudo groundtruth, we are able to conveniently train any existing image segmentation models without increasing the costs of annotations or modifying the models’ architectures. Moreover, we explore different strategies for allocating labeling effort in semi-supervised scene segmentation, and find that a combination of finely-labeled samples and coarsely-labeled samples performs better than the traditional dense-fine only annotations. Extensive experiments on datasets including Cityscapes and KITTI are conducted to evaluate our proposed methods. The results demonstrate that GSR can be easily applied to boost the performance of existing models like PSPNet, DeepLabv3+, etc with reduced annotations. With half of the annotation effort, GSR achieves 99% of the accuracy of its fully supervised state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene. However, such strong supervision suffers from large annotation costs, arousing the need to study efficient annotating. In this paper, we discover that the locations of instances matter for both instance and semantic 3D scene segmentation. By fully taking advantage of locations, we design a weakly-supervised point cloud segmentation method that only requires clicking on one point per instance to indicate its location for annotation. With over-segmentation for pre-processing, we extend these location annotations into segments as seg-level labels. We further design a segment grouping network (SegGroup) to generate point-level pseudo labels under seg-level labels by hierarchically grouping the unlabeled segments into the relevant nearby labeled segments, so that existing point-level supervised segmentation models can directly consume these pseudo labels for training. Experimental results show that our seg-level supervised method (SegGroup) achieves comparable results with the fully annotated point-level supervised methods. Moreover, it outperforms the recent weakly-supervised methods given a fixed annotation budget. Code is available at https://github.com/antao97/SegGroup. [ABSTRACT FROM AUTHOR]

The existing publicly available datasets with pixel-level labels contain limited categories, and it is difficult to generalize to the real world containing thousands of categories. In this paper, we propose an approach to generate object masks with detailed pixel-level structures/boundaries automatically to enable semantic image segmentation of thousands of targets in the real world without manually labelling. A Guided Filter Network (GFN) is first developed to learn the segmentation knowledge from an existed dataset, and such GFN then transfers the learned segmentation knowledge to generate initial coarse object masks for the target images. These coarse object masks are treated as pseudo labels to self-optimize the GFN iteratively in the target images. Our experiments on six image sets have demonstrated that our proposed approach can generate object masks with detailed pixel-level structures/boundaries, whose quality is comparable to the manually-labelled ones. Our proposed approach also achieves better performance on semantic image segmentation than most existing weakly-supervised, semi-supervised, and domain adaptation approaches under the same experimental conditions. [ABSTRACT FROM AUTHOR]

Most of the existing named entity recognition methods require a large amount of annotated data to obtain good performance. Once the annotated data are insufficient, the performance of these methods will degrade significantly. However, data annotation is time-consuming and laborious work. Therefore, how to achieve better performance with small amounts of annotated data in the named entity recognition task is an urgent task to be solved. In real scenarios, human beings always rely on some other words in the sentence when they recognize named entities, these words are called triggers. Motivated by this, we first verified the effectiveness of entity triggers for named entity recognition, then constructed a dual learning framework for low-resource named entity recognition based on the duality of entity triggers and corresponding entity, termed DualNER. Experiments show that the proposed methods use 20% trigger-entity annotated data and can achieve comparable results with the conventional model, which is trained by 50%–70% conventional annotated data. [ABSTRACT FROM AUTHOR]

Obstructive sleep apnea (OSA) is one of the most commonsleep-related breathing disorders. Nearly 1 billion people worldwide suffer from it, causing serious health effects and social burden. However, traditional monitoring systems often fall short in terms of cost and accessibility. In this article, we first propose a deep active learning model to detect OSA events from electrocardiogram (ECG). We then designed and developed a prototype of OSA monitoring system using an ECG sensor and smartphone, in which our OSA detection algorithm is implemented and validated. Experiments show that we achieve accuracy of 92.15% while using 40% of labeled data, significantly reducing the cost of labeling and maximizing the performance. According to detection results and health-related multimedia signals, we provide OSA risk level and medical advice to the users. We believe that the multimedia monitoring system can efficiently help diagnose OSA, which could lead to effective intervention strategies and better sleep care. [ABSTRACT FROM AUTHOR]

Active learning (AL) improves the generalization performance for the current classification hypothesis by querying labels from a pool of unlabeled data. The sampling process is typically assessed by an informative, representative, or diverse evaluation policy. However, the policy, which needs an initial labeled set to start, may degenerate its performance in a cold-start hypothesis. In this article, we first show that typical AL sampling can be equivalently formulated as geometric sampling over minimum enclosing ballsMEB of this article denotes a conceptual geometry over the cluster in generalization analysis. In the SVM community, it is related to hard-margin support vector data description.(MEBs) of clusters. Following the $\gamma $ -tube structure in geometric clustering, we then divide one MEB covering a cluster into two parts: 1) a $\gamma $ -tube and 2) a $\gamma $ -ball. By estimating the error disagreement between sampling in MEB and $\gamma $ -ball, our theoretical insight reveals that $\gamma $ -tube can effectively measure the disagreement of hypotheses in original space over MEB and sampling space over $\gamma $ -ball. To tighten our insight, we present generalization analysis, and the results show that sampling in $\gamma $ -tube can derive higher probability bound to achieve a nearly zero generalization error. With these analyses, we finally apply the informative sampling policy of AL over $\gamma $ -tube to present a tube AL (TAL) algorithm against the cold-start sampling issue. As a result, the dependency between the querying process and the evaluation policy of active sampling can be alleviated. Experimental results show that by using the $\gamma $ -tube structure to deal with cold-start sampling, TAL achieves the superior performance than standard AL evaluation baselines by presenting substantial accuracy improvements. Image edge recognition extends our theoretical results. [ABSTRACT FROM AUTHOR]

Unavailability of large training datasets is a bottleneck that needs to be overcome to realize the true potential of deep learning in histopathology applications. Although slide digitization via whole slide imaging scanners has increased the speed of data acquisition, labeling of virtual slides requires a substantial time investment from pathologists. Eye gaze annotations have the potential to speed up the slide labeling process. This work explores the viability and timing comparisons of eye gaze labeling compared to conventional manual labeling for training object detectors. Challenges associated with gaze based labeling and methods to refine the coarse data annotations for subsequent object detection are also discussed. Results demonstrate that gaze tracking based labeling can save valuable pathologist time and delivers good performance when employed for training a deep object detector. Using the task of localization of Keratin Pearls in cases of oral squamous cell carcinoma as a test case, we compare the performance gap between deep object detectors trained using hand-labelled and gaze-labelled data. On average, compared to ‘Bounding-box’ based hand-labeling, gaze-labeling required 57.6% less time per label and compared to ‘Freehand’ labeling, gaze-labeling required on average 85% less time per label. [ABSTRACT FROM AUTHOR]

Software fault prediction models help the software quality assurance team to manage the resources optimally during software maintenance. Most of the recently proposed fault prediction approaches are helpful on labeled datasets only. Recently, several threshold-based software fault prediction approaches have been proposed. However, these approaches do not incorporate the distribution of software metrics for metric threshold derivation; hence, they demonstrate poor performance. To fill this gap, we develop an automated fault prediction approach, namely threshold clustering labeling/threshold clustering labeling plus (TCLP), which does not need a labeled dataset. It can identify the faulty and nonfaulty artifacts on unlabeled datasets by self-learning. Our proposed approach is an extension of the state-of-the-art technique known as CLAMI. Unlike CLAMI, we derive the metrics threshold using logarithmic transformation. Thereafter, we label the instances into binary classes (faulty/nonfaulty) using the metric threshold values. TCLP extends this approach one step further by performing fault prediction using a random forest algorithm. The empirical evaluation of the proposed approach on 28 datasets (with the different number of metrics and granularity) collected from five software groups shows that the proposed unsupervised method obtains significantly better results than those of the state-of-the-art methods. The proposed approach impressively enhances the performance of CLAMI in terms of accuracy, F-measure, and Mathew’s correlation coefficient. [ABSTRACT FROM AUTHOR]

Ultrasound imaging is a commonly used technology for visualising patient anatomy in real-time during diagnostic and therapeutic procedures. High operator dependency and low reproducibility make ultrasound imaging and interpretation challenging with a steep learning curve. Automatic image classification using deep learning has the potential to overcome some of these challenges by supporting ultrasound training in novices, as well as aiding ultrasound image interpretation in patient with complex pathology for more experienced practitioners. However, the use of deep learning methods requires a large amount of data in order to provide accurate results. Labelling large ultrasound datasets is a challenging task because labels are retrospectively assigned to 2D images without the 3D spatial context available in vivo or that would be inferred while visually tracking structures between frames during the procedure. In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure. We use a CNN composed of two branches, one for voice data and another for image data, which are joined to predict image labels from the spoken names of anatomical landmarks. The network was trained using recorded verbal comments from expert operators. Our results show a prediction accuracy of 76% at image level on a dataset with 5 different labels. We conclude that the addition of spoken commentaries can increase the performance of ultrasound image classification, and eliminate the burden of manually labelling large EUS datasets necessary for deep learning applications. [ABSTRACT FROM AUTHOR]

Multi-label learning deals with training examples each represented by a single instance while associated with multiple class labels. Due to the exponential number of possible label sets to be considered by the predictive model, it is commonly assumed that label correlations should be well exploited to design an effective multi-label learning approach. On the other hand, class-imbalance stands as an intrinsic property of multi-label data which significantly affects the generalization performance of the multi-label predictive model. For each class label, the number of training examples with positive labeling assignment is generally much less than those with negative labeling assignment. To deal with the class-imbalance issue for multi-label learning, a simple yet effective class-imbalance aware learning strategy called cross-coupling aggregation (COCOA) is proposed in this article. Specifically, COCOA works by leveraging the exploitation of label correlations as well as the exploration of class-imbalance simultaneously. For each class label, a number of multiclass imbalance learners are induced by randomly coupling with other labels, whose predictions on the unseen instance are aggregated to determine the corresponding labeling relevancy. Extensive experiments on 18 benchmark datasets clearly validate the effectiveness of COCOA against state-of-the-art multi-label learning approaches especially in terms of imbalance-specific evaluation metrics. [ABSTRACT FROM AUTHOR]

It is difficult to detect defects such as shallow dents and rust on rolling surfaces by using the traditional vision-based surface inspection method (line light source and line array camera mode) which has a low sensitivity to these defects. This paper presents a method that introduces the fringe projection technique for traditional visual inspection devices to overcome the limitations of the traditional methods and uses deep-learning techniques for detecting defects such as cuts, abrasions, dents, and rust on the rolling surfaces of drum-shaped rollers. A new artificial-intelligence-based labeling method, namely, the Padua Incremental Mask Labeling Method, has been introduced for accelerating the calibration process used for defect detection, and based on a one-stage architecture, the You-Only-Look-Once-OurNet (YOLO-OurNet) deep-learning network has been designed for detecting the defects on the rolling surfaces of drum-shaped rollers. From the results of the experimental tests, the time required for detecting a defect has been found to be 0.024s, an accuracy rate of up to 99.2%, and the value of object detection evaluation index F1 of up to 0.988. Our method outperforms the related method on the domain of rolling surface defect detection. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a key component in various text mining applications. Numerous sentiment classification techniques, including conventional and deep-learning-based methods, have been proposed in the literature. In most existing methods, a high-quality training set is assumed to be given. Nevertheless, constructing a high-quality training set that consists of highly accurate labels is challenging in real applications. This difficulty stems from the fact that text samples usually contain complex sentiment representations, and their annotation is subjective. We address this challenge in this study by leveraging a new labeling strategy and utilizing a two-level long short-term memory network to construct a sentiment classifier. Lexical cues are useful for sentiment analysis, and they have been utilized in conventional studies. For example, polar and negation words play important roles in sentiment analysis. A new encoding strategy, that is, $\rho $ -hot encoding, is proposed to alleviate the drawbacks of one-hot encoding and, thus, effectively incorporate useful lexical cues. Moreover, the sentimental polarity of a word may change in different sentences due to label noise or context. A flipping model is proposed to model the polar flipping of words in a sentence. We compile three Chinese datasets on the basis of our label strategy and proposed methodology. Experiments demonstrate that the proposed method outperforms state-of-the-art algorithms on both benchmark English data and our compiled Chinese data. [ABSTRACT FROM AUTHOR]

Usually considered as a classification problem, entity resolution (ER) can be very challenging on real data due to the prevalence of dirty values. The state-of-the-art solutions for ER were built on a variety of learning models (most notably deep neural networks), which require lots of accurately labeled training data. Unfortunately, high-quality labeled data usually require expensive manual work, and are therefore not readily available in many real scenarios. In this paper, we propose a novel learning paradigm for ER, called gradual machine learning, which aims to enable effective machine labeling without the requirement for manual labeling effort. It begins with some easy instances in a task, which can be automatically labeled by the machine with high accuracy, and then gradually labels more challenging instances by iterative factor graph inference. In gradual machine learning, the hard instances in a task are gradually labeled in small stages based on the estimated evidential certainty provided by the labeled easier instances. Our extensive experiments on real data have shown that the performance of the proposed approach is considerably better than its unsupervised alternatives, and highly competitive compared to the state-of-the-art supervised techniques. Using ER as a test case, we demonstrate that gradual machine learning is a promising paradigm potentially applicable to other challenging classification tasks requiring extensive labeling effort. [ABSTRACT FROM AUTHOR]

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models with sacrifice in accuracy, most are geared toward either supervised or unsupervised learning. Yet two observations inspired us to wonder whether semi-supervised learning might be useful to solve discrimination problems. First, previous study showed that increasing the size of the training set may lead to a better trade-off between fairness and accuracy. Second, the most powerful models today require an enormous of data to train which, in practical terms, is likely possible from a combination of labeled and unlabeled data. Hence, in this paper, we present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data, a re-sampling method to obtain multiple fair datasets and lastly, ensemble learning to improve accuracy and decrease discrimination. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning. A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination. [ABSTRACT FROM AUTHOR]

As training high-performance object detectors requires expensive bounding box annotations, recent methods resort to free-available image captions. However, detectors trained on caption supervision perform poorly because captions are usually noisy and cannot provide precise location information. To tackle this issue, we present a visual analysis method, which tightly integrates caption supervision with object detection to mutually enhance each other. In particular, object labels are first extracted from captions, which are utilized to train the detectors. Then, the objects detected from images are fed into caption supervision for further improvement. To effectively loop users into the object detection process, a node-link-based set visualization supported by a multi-type relational co-clustering algorithm is developed to explain the relationships between the extracted labels and the images with detected objects. The co-clustering algorithm clusters labels and images simultaneously by utilizing both their representations and their relationships. Quantitative evaluations and a case study are conducted to demonstrate the efficiency and effectiveness of the developed method in improving the performance of object detectors. [ABSTRACT FROM AUTHOR]

With the lack of failure data, class imbalance has become a common challenge in the fault diagnosis of industrial systems. The oversampling methods can tackle the class-imbalanced problem by generating the minority samples to balance the training set. However, one of the main challenges of the existing oversampling methods is how to generate high-quality minority samples. Traditional oversampling methods regard all synthetic samples as minority ones to be added to the training set without filtering. The low-quality synthetic samples would distort the distribution of the dataset and worsen the classification performance. In this article, we propose a weakly supervised oversampling method that treats all synthetic samples as unlabeled samples and develops a graph semisupervised learning algorithm to select high-quality synthetic samples, adding into the final training set as minority samples. To improve the quality of synthetic samples, we propose a cost-sensitive neighborhood component analysis dimensionality reduction method to enhance domain information validity in high-dimensional datasets. Finally, combining a boosting-based ensemble framework, we propose a new imbalanced learning framework suitable for high dimensionality and highly imbalanced fault diagnosis in industrial systems. The experimental validation is performed on five real-world wind turbine blade cracking failure datasets and compared to 15 benchmark methods. The experimental results show that average performances and robustness of the proposed framework are significantly better than those of the benchmark methods. [ABSTRACT FROM AUTHOR]

With increasing data volumes, the bottleneck in obtaining data for training a given learning task is the cost of manually labeling instances within the data. To alleviate this issue, various reduced label settings have been considered including semi-supervised learning, partial- or incomplete-label learning, multiple-instance learning, and active learning. Here, we focus on multiple-instance multiple-label learning with missing bag labels. Little research has been done for this challenging yet potentially powerful variant of incomplete supervision learning. We introduce a novel discriminative probabilistic model for missing labels in multiple-instance multiple-label learning. To address inference challenges, we introduce an efficient implementation of the EM algorithm for the model. Additionally, we consider an alternative inference approach that relies on maximizing the label-wise marginal likelihood of the proposed model instead of the joint likelihood. Numerical experiments on benchmark datasets illustrate the robustness of the proposed approach. In particular, comparison to state-of-the-art methods shows that our approach introduces a significantly smaller decrease in performance when the proportion of missing labels is increased. [ABSTRACT FROM AUTHOR]

Federated learning enables local devices to jointly train the server model while keeping the data decentralized and private. In federated learning, all local data should be annotated by alternative labeling techniques since the annotator in the server cannot access the data. Therefore, it is hardly guaranteed that they are correctly annotated. Under this noisy label setting, local models form inconsistent class decision boundaries with one another, and their weights severely diverge, which are serious problems in federated learning. To solve these problems, we introduce a novel federated learning scheme that allows the server to cooperate with local models by interchanging class-wise centroids. The server aligns the class-wise centroids, which are central features of local data on each device, and broadcasts aligned centroids to selected clients every communication round. Updating local models with the aligned centroids helps us to form consistent class decision boundaries among local models, although the noise distributions in clients' data are different from each other. Furthermore, we introduce a sample selection approach to filter out data with noisy labels and a label correction method to adjust the labels of noisy instances. Our experimental results show that our approach is noticeably effective in federated learning with noisy labels. [ABSTRACT FROM AUTHOR]

Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-supervised learning, exploiting a small portion of labelled data and large amounts of unlabelled data. The major challenge, however, is the accumulated label errors through auto-labelling, compromising the training. In this paper, we present an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling. Specifically, we introduce a multi-agent method, named GroupNet (GN), to endow our solution with the ability to identify the wrongly-labelled samples and preserve the clean samples. We show that GN alone achieves the leading accuracy in traditional supervised face recognition even when the noisy labels take over 50% of the training data. Further, we develop a semi-supervised face recognition solution, named Noise Robust Learning-Labelling (NRoLL), which is based on the robust training ability empowered by GN. It starts with a small amount of labelled data and consequently conducts high-confidence labelling on a large amount of unlabelled data to boost further training. The more data is labelled by NRoLL, the higher confidence is with the label in the dataset. To evaluate the competitiveness of our method, we run NRoLL with a rough condition that only one-fifth of the labelled MSCeleb is available and the rest is used as unlabelled data. On a wide range of benchmarks, our method compares favorably against the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we target at the Fine-grAined human-Centric Tracklet Segmentation (FACTS) problem, where 12 human parts, e.g., face, pants, left-leg, are segmented. To reduce the heavy and tedious labeling efforts, FACTS requires only one labeled frame per video during training. The small size of human parts and the labeling scarcity makes FACTS very challenging. Considering adjacent frames of videos are continuous and human usually do not change clothes in a short time, we explicitly consider the pixel-level and frame-level context in the proposed Temporal Context segmentation Network (TCNet). On the one hand, optical flow is on-line calculated to propagate the pixel-level segmentation results to neighboring frames. On the other hand, frame-level classification likelihood vectors are also propagated to nearby frames. By fully exploiting the pixel-level and frame-level context, TCNet indirectly uses the large amount of unlabeled frames during training and produces smooth segmentation results during inference. Experimental results on four video datasets show the superiority of TCNet over the state-of-the-arts. The newly annotated datasets can be downloaded via http://liusi-group.com/projects/FACTS for the further studies. [ABSTRACT FROM AUTHOR]

Traditional classification learning algorithms have several limitations: 1) they are time consuming for the large-scale training multivariate time-series (MTS) data, and unsuitable for the dynamically added training data; 2) as the number of the training MTS data becomes larger, they could not achieve the desired classification accuracy; 3) most of them do not consider how to make use of the unlabeled samples to enhance the classifier performance; and 4) due to the high dimension of MTS and complex relationship among variables, existing online learning algorithms are not effective to update shapelet-based association rules. Up to now, few work touched online classification learning for dynamically added unlabeled examples. To efficiently address these issues, we propose an online rule-based classifier learning framework on dynamically added unlabeled MTS data (ORCL-U). This framework integrates a confidence-based labeling strategy (CLS) and an online rule-based classifier learning approach (ORBCL). Extensive experiments on ten datasets show the effectiveness and efficiency of our proposed approach. [ABSTRACT FROM AUTHOR]

Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new $2n$ -slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is playing an increasingly important role in processing large amounts of data generated by communication networks, since it can efficiently solve the problems of non-linearity and unstructured data. Recently, ML has been widely used in the processing of wireless channel data, as the noisy channel in real propagation environment is usually non-linear and unstructured. In this paper, a denoising method based on ML is presented. Two ML algorithms are used to classify and remove noise in channel impulse responses. Then, the results of the traditional noise threshold denoising are compared with ML denoising, and it is found that the denoising classifier using the bidirectional recurrent neural network has the better denoising performance. Finally, some channel parameters such as RMS delay spread are estimated based on measured channel data using different denoising methods. The results are evaluated and compared to explore the impact of denoising method on the extracted channel parameters. [ABSTRACT FROM AUTHOR]

Acquisition of labeled training samples for affective computing is usually costly and time-consuming, as affects are intrinsically subjective, subtle and uncertain, and hence multiple human assessors are needed to evaluate each affective sample. Particularly, for affect estimation in the 3D space of valence, arousal and dominance, each assessor has to perform the evaluations in three dimensions, which makes the labeling problem even more challenging. Many sophisticated machine learning approaches have been proposed to reduce the data labeling requirement in various other domains, but so far few have considered affective computing. This paper proposes two multi-task active learning for regression approaches, which select the most beneficial samples to label, by considering the three affect primitives simultaneously. Experimental results on the VAM corpus demonstrated that our optimal sample selection approaches can result in better estimation performance than random selection and several traditional single-task active learning approaches. Thus, they can help alleviate the data labeling problem in affective computing, i.e., better estimation performance can be obtained from fewer labeling queries. [ABSTRACT FROM AUTHOR]

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a class-attribute matrix to define which classes have which attributes. Designing a suitable class-attribute matrix is the key to the subsequent procedure, but this design process is tedious and trial-and-error with no guidance. This paper proposes a visual explainable active learning approach with its design and implementation called semantic navigator to solve the above problems. This approach promotes human-AI teaming with four actions (ask, explain, recommend, respond) in each interaction loop. The machine asks contrastive questions to guide humans in the thinking process of attributes. A novel visualization called semantic map explains the current status of the machine. Therefore analysts can better understand why the machine misclassifies objects. Moreover, the machine recommends the labels of classes for each attribute to ease the labeling burden. Finally, humans can steer the model by modifying the labels interactively, and the machine adjusts its recommendations. The visual explainable active learning approach improves humans' efficiency of building zero-shot classification models interactively, compared with the method without guidance. We justify our results with user studies using the standard benchmarks for zero-shot classification. [ABSTRACT FROM AUTHOR]

Multitemporal remote-sensing images play a key role as a source of information for automated crop mapping and monitoring. The spatial/spectral pattern evolution along time provides information about the dynamics of the crops and are very useful for productivity estimation. Although the multitemporal mapping of crops has progressed considerably with the advent of deep learning in recent years, the classification models obtained still have limitations when exposed to unknown classes in the prediction phase, reducing their usefulness. In other words, these models are trained to identify a closed set of crops (e.g., soy and sugar cane) and are therefore unable to recognize other types of crops (e.g., maize). In this letter, we deal with the challenges of multitemporal crop recognition by proposing a new approach called OpenPCS++ that is not only able to learn known classes but is also capable of identifying new crops in the predicting phase. The proposed approach was evaluated in two challenging public datasets located in tropical climates in Brazil. Results showed that OpenPCS++ achieved increases of up to 0.19 in terms of area under the receiver-operating characteristic (ROC) curve in comparison with baselines. Code is available at https://github.com/DiMorten/osss-mcr. [ABSTRACT FROM AUTHOR]

In this paper, one-shot person re-identification (person re-ID) task is brought into focus, where there is only one labeled sample of each pedestrian. Existing one-shot person re-ID researches usually utilize data insufficiently or treat both labeled and pseudo-labeled data in the same way. To solve these problems, we propose a Hierarchical Pseudo Labeling strategy based on Density and Distance and an Embranchment Learning framework. The pseudo labeling strategy can fully exploit the unlabeled data information and generate accurate pseudo labels by multiple clustering based on pairwise feature distances and distribution densities hierarchically. Our Embranchment Learning framework learns data in an individualized way by feeding data with labels from different sources into distinct network branches paired with personalized loss functions. Besides, Batch Distance Loss and Global Center Loss are designed to target the characteristics of distinct input data. They are capable of distinguishing diverse categories and reducing the intra-class distance respectively. Our method outperforms the existing state-of-the-art algorithm by 36.1, 28.7 of mAP and shortens the training time 6 and 10 epochs on Market-1501 and DukeMTMC-reID respectively. [ABSTRACT FROM AUTHOR]

In multi-instance learning (MIL), labels are associated with bags rather than the instances in the bag. Most of the previous MIL methods assume that each bag has the actual label in the training set. However, from the process of labeling work, the label of a bag is always evaluated by the calculation of the labels obtained from a number of labelers. In the calculation, the weight of each labeler is always unknown and people always assign the weight for each labeler by random or equally, and this may result in the ambiguous labels for the bags, which is called weak labels here. In addition, we always meet the problem of knowledge transfer from the source task to the target task, and this leads to the study of multiple instance transfer learning. In this article, we propose a new framework called transfer learning-based multiple instance learning (TMIL) framework to address the problem of multiple instance transfer learning in which both the source task and the target task contain the weak labels. We first construct a TMIL model with weak labels, which can transfer knowledge from the source task to the target task where both source and target tasks contain weak labels. We then put forward an iterative framework to solve the transfer learning model with weak labels so that we can update the label of the bag to improve the performance of multiple instance learning. We then present the convergence analysis of the proposed method. The experiments show that the proposed method outperforms the existing multiple instance learning methods and can correct the initial labels to obtain the actual labels for the bags. [ABSTRACT FROM AUTHOR]