Search

This paper presents FaceXHuBERT, a text-less speech-driven 3D facial animation generation method that allows to capture personalized and subtle cues in speech (e.g. identity, emotion and hesitation). It is also very robust to background noise and can handle audio recorded in a variety of situations (e.g. multiple people speaking). Recent approaches employ end-to-end deep learning taking into account both audio and text as input to generate facial animation for the whole face. However, scarcity of publicly available expressive audio-3D facial animation datasets poses a major bottleneck. The resulting animations still have issues regarding accurate lip-synching, expressivity, person-specific information and generalizability. We effectively employ self-supervised pretrained HuBERT model in the training process that allows us to incorporate both lexical and non-lexical information in the audio without using a large lexicon. Additionally, guiding the training with a binary emotion condition and speaker identity distinguishes the tiniest subtle facial motion. We carried out extensive objective and subjective evaluation in comparison to ground-truth and state-of-the-art work. A perceptual user study demonstrates that our approach produces superior results with respect to the realism of the animation 78% of the time in comparison to the state-of-the-art. In addition, our method is 4 times faster eliminating the use of complex sequential models such as transformers. We strongly recommend watching the supplementary video before reading the paper. We also provide the implementation and evaluation codes with a GitHub repository link., Comment: 13 pages, 4 figures, code included

Recent advancements in technology have expanded the possibilities of human action recognition by leveraging 3D data, which offers a richer representation of actions through the inclusion of depth information, enabling more accurate analysis of spatial and temporal characteristics. However, 3D human action recognition is a challenging task due to the irregularity and Disarrangement of the data points in action sequences. In this context, we present our novel model for human action recognition from fixed topology mesh sequences based on Spiral Auto-encoder and Transformer Network, namely SpATr. The proposed method first disentangles space and time in the mesh sequences. Then, an auto-encoder is utilized to extract spatial geometrical features, and tiny transformer is used to capture the temporal evolution of the sequence. Previous methods either use 2D depth images, sample skeletons points or they require a huge amount of memory leading to the ability to process short sequences only. In this work, we show competitive recognition rate and high memory efficiency by building our auto-encoder based on spiral convolutions, which are light weight convolution directly applied to mesh data with fixed topologies, and by modeling temporal evolution using a attention, that can handle large sequences. The proposed method is evaluated on on two 3D human action datasets: MoVi and BMLrub from the Archive of Motion Capture As Surface Shapes (AMASS). The results analysis shows the effectiveness of our method in 3D human action recognition while maintaining high memory efficiency. The code will soon be made publicly available., Comment: 10 pages, 5 figures, Submitted IVC

Deep neural networks (DNNs) have demonstrated their effectiveness in a wide range of computer vision tasks, with the state-of-the-art results obtained through complex and deep structures that require intensive computation and memory. Now-a-days, efficient model inference is crucial for consumer applications on resource-constrained platforms. As a result, there is much interest in the research and development of dedicated deep learning (DL) hardware to improve the throughput and energy efficiency of DNNs. Low-precision representation of DNN data-structures through quantization would bring great benefits to specialized DL hardware. However, the rigorous quantization leads to a severe accuracy drop. As such, quantization opens a large hyper-parameter space at bit-precision levels, the exploration of which is a major challenge. In this paper, we propose a novel framework referred to as the Fixed-Point Quantizer of deep neural Networks (FxP-QNet) that flexibly designs a mixed low-precision DNN for integer-arithmetic-only deployment. Specifically, the FxP-QNet gradually adapts the quantization level for each data-structure of each layer based on the trade-off between the network accuracy and the low-precision requirements. Additionally, it employs post-training self-distillation and network prediction error statistics to optimize the quantization of floating-point values into fixed-point numbers. Examining FxP-QNet on state-of-the-art architectures and the benchmark ImageNet dataset, we empirically demonstrate the effectiveness of FxP-QNet in achieving the accuracy-compression trade-off without the need for training. The results show that FxP-QNet-quantized AlexNet, VGG-16, and ResNet-18 reduce the overall memory requirements of their full-precision counterparts by 7.16x, 10.36x, and 6.44x with less than 0.95%, 0.95%, and 1.99% accuracy drop, respectively., Comment: 30 pages, 12 figures, 5 tables. in IEEE Access, 2022

The detection and localization of possible diseases in crops are usually automated by resorting to supervised deep learning approaches. In this work, we tackle these goals with unsupervised models, by applying three different types of autoencoders to a specific open-source dataset of healthy and unhealthy pepper and cherry leaf images. CAE, CVAE and VQ-VAE autoencoders are deployed to screen unlabeled images of such a dataset, and compared in terms of image reconstruction, anomaly removal, detection and localization. The vector-quantized variational architecture turns out to be the best performing one with respect to all these targets., 23 pages, 8 figures

In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets. Despite this, the trained object detectors typically do not reliably assess uncertainty regarding their own knowledge, and the quality of their probabilistic predictions is usually poor. As these are often used to make subsequent decisions, such inaccurate probabilistic predictions must be avoided. In this work, we investigate the uncertainty calibration properties of different pretrained object detection architectures in a multi-class setting. We propose a framework to ensure a fair, unbiased, and repeatable evaluation and conduct detailed analyses assessing the calibration under distributional changes (e.g., distributional shift and application to out-of-distribution data). Furthermore, by investigating the influence of different detector paradigms, post-processing steps, and suitable choices of metrics, we deliver novel insights into why poor detector calibration emerges. Based on these insights, we are able to improve the calibration of a detector by simply finetuning its last layer., 17 pages, 6 figures, submitted to IJCV

Local patterns play an important role in statistical physics as well as in image processing. Two-dimensional ordinal patterns were studied by Ribeiro et al. who determined permutation entropy and complexity in order to classify paintings and images of liquid crystals. Here we find that the 2 by 2 patterns of neighboring pixels come in three types. The statistics of these types, expressed by two parameters, contains the relevant information to describe and distinguish textures. The parameters are most stable and informative for isotropic structures., Comment: 20 pages, 10 figures

Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key to narrowing the communication gap between hard and non-hard of hearing people. Our method explores a geometric feature space that we call `sub-skeleton' aspects of movement. We assess similarity of feature space trajectories using natural, speed invariant distance measures, which enables clear and insightful nearest neighbor classification. The simplicity and scalability of our basic method allows for immediate application in different data domains with little to no parameter tuning. We demonstrate the effectiveness of our basic method, and a boosted variation, with experiments on data from different application domains and tracking technologies. Surprisingly, our simple methods improve sign recognition over recent, state-of-the-art approaches., To appear in Proc. of the 27th International Conference on Database Systems for Advanced Applications (DASFAA-2022)

Early detection of breast cancer in mammography screening via deep-learning based computer-aided detection systems shows promising potential in improving the curability and mortality rates of breast cancer. However, many clinical centres are restricted in the amount and heterogeneity of available data to train such models to (i) achieve promising performance and to (ii) generalise well across acquisition protocols and domains. As sharing data between centres is restricted due to patient privacy concerns, we propose a potential solution: sharing trained generative models between centres as substitute for real patient data. In this work, we use three well known mammography datasets to simulate three different centres, where one centre receives the trained generator of Generative Adversarial Networks (GANs) from the two remaining centres in order to augment the size and heterogeneity of its training dataset. We evaluate the utility of this approach on mammography patch classification on the test set of the GAN-receiving centre using two different classification models, (a) a convolutional neural network and (b) a transformer neural network. Our experiments demonstrate that shared GANs notably increase the performance of both transformer and convolutional classification models and highlight this approach as a viable alternative to inter-centre data sharing., Comment: Draft accepted as oral presentation at International Workshop on Breast Imaging (IWBI) 2022. 9 pages, 3 figures

Unlike human daily activities, existing publicly available sensor datasets for work activity recognition in industrial domains are limited by difficulties in collecting realistic data as close collaboration with industrial sites is required. This also limits research on and development of AI methods for industrial applications. To address these challenges and contribute to research on machine recognition of work activities in industrial domains, in this study, we introduce a new large-scale dataset for packaging work recognition called OpenPack. OpenPack contains 53.8 hours of multimodal sensor data, including keypoints, depth images, acceleration data, and readings from IoT-enabled devices (e.g., handheld barcode scanners used in work procedures), collected from 16 distinct subjects with different levels of packaging work experience. On the basis of this dataset, we propose a neural network model designed to recognize work activities, which efficiently fuses sensor data and readings from IoT-enabled devices by processing them within different streams in a ladder-shaped architecture, and the experiment showed the effectiveness of the architecture. We believe that OpenPack will contribute to the community of action/activity recognition with sensors. OpenPack dataset is available at https://open-pack.github.io/.

Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image models have overcome this limitation of image resolution but are prohibitively slow and unidirectional as they generate tokens via element-wise autoregressive sampling from the prior. By contrast, in this paper we propose a novel discrete diffusion probabilistic model prior which enables parallel prediction of Vector-Quantized tokens by using an unconstrained Transformer architecture as the backbone. During training, tokens are randomly masked in an order-agnostic manner and the Transformer learns to predict the original tokens. This parallelism of Vector-Quantized token prediction in turn facilitates unconditional generation of globally consistent high-resolution and diverse imagery at a fraction of the computational expense. In this manner, we can generate image resolutions exceeding that of the original training set samples whilst additionally provisioning per-image likelihood estimates (in a departure from generative adversarial approaches). Our approach achieves state-of-the-art results in terms of Density (LSUN Bedroom: 1.51; LSUN Churches: 1.12; FFHQ: 1.20) and Coverage (LSUN Bedroom: 0.83; LSUN Churches: 0.73; FFHQ: 0.80), and performs competitively on FID (LSUN Bedroom: 3.64; LSUN Churches: 4.07; FFHQ: 6.11) whilst offering advantages in terms of both computation and reduced training set requirements., 19 pages, 14 figures

Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship Recognition (LTVRR). LTVRR aims at improving the learning of structured visual relationships that come from the long-tail (e.g., "rabbit grazing on grass"). In this setup, the subject, relation, and object classes each follow a long-tail distribution. To begin our study and make a future benchmark for the community, we introduce two LTVRR-related benchmarks, dubbed VG8K-LT and GQA-LT, built upon the widely used Visual Genome and GQA datasets. We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup. Lastly, we propose a visiolinguistic hubless (VilHub) loss and a Mixup augmentation technique adapted to LTVRR setup, dubbed as RelMix. Both VilHub and RelMix can be easily integrated on top of existing models and despite being simple, our results show that they can remarkably improve the performance, especially on tail classes. Benchmarks, code, and models have been made available at: https://github.com/Vision-CAIR/LTVRR.

Providing early diagnosis of cerebral palsy (CP) is key to enhancing the developmental outcomes for those affected. Diagnostic tools such as the General Movements Assessment (GMA), have produced promising results in early diagnosis, however these manual methods can be laborious. In this paper, we propose a new framework for the automated classification of infant body movements, based upon the GMA, which unlike previous methods, also incorporates a visualization framework to aid with interpretability. Our proposed framework segments extracted features to detect the presence of Fidgety Movements (FMs) associated with the GMA spatiotemporally. These features are then used to identify the body-parts with the greatest contribution towards a classification decision and highlight the related body-part segment providing visual feedback to the user. We quantitatively compare the proposed framework's classification performance with several other methods from the literature and qualitatively evaluate the visualization's veracity. Our experimental results show that the proposed method performs more robustly than comparable techniques in this setting whilst simultaneously providing relevant visual interpretability., Comment: Proceedings of the 2021 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), accepted, 2021

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on accumulating knowledge and avoiding forgetting, assuming information once learned should be stored. Data stream mining focuses on adaptation to concept drift and discarding outdated information, assuming that only the most recent data is relevant. While these two areas are mainly being developed in separation, they offer complementary views on the problem of learning from dynamic data. There is a need for unifying them, by offering architectures capable of both learning and storing new information, as well as revisiting and adapting to changes in previously seen concepts. We propose a novel continual learning approach that can handle both tasks. Our experience replay method is fueled by a centroid-driven memory storing diverse instances of incrementally arriving classes. This is enhanced with a reactive subspace buffer that tracks concept drift occurrences in previously seen classes and adapts clusters accordingly. The proposed architecture is thus capable of both remembering valid and forgetting outdated information, offering a holistic framework for continual learning under concept drift., IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021

A novel image matching method is proposed that utilizes learned features extracted by an off-the-shelf deep neural network to obtain a promising performance. The proposed method uses pre-trained VGG architecture as a feature extractor and does not require any additional training specific to improve matching. Inspired by well-established concepts in the psychology area, such as the Mental Rotation paradigm, an initial warping is performed as a result of a preliminary geometric transformation estimate. These estimates are simply based on dense matching of nearest neighbors at the terminal layer of VGG network outputs of the images to be matched. After this initial alignment, the same approach is repeated again between reference and aligned images in a hierarchical manner to reach a good localization and matching performance. Our algorithm achieves 0.57 and 0.80 overall scores in terms of Mean Matching Accuracy (MMA) for 1 pixel and 2 pixels thresholds respectively on Hpatches dataset, which indicates a better performance than the state-of-the-art., Comment: CVPR 2021 Image Matching Workshop Camera Ready Version

Medical segmentation is performed to determine the bounds of regions of interest (ROI) prior to surgery. By allowing the study of growth, structure, and behaviour of the ROI in the planning phase, critical information can be obtained, increasing the likelihood of a successful operation. Usually, segmentations are performed manually or via machine learning methods trained on manual annotations. In contrast, this paper proposes a fully automatic, unsupervised inpainting-based brain tumour segmentation system for T1-weighted MRI. First, a deep convolutional neural network (DCNN) is trained to reconstruct missing healthy brain regions. Then, upon application, anomalous regions are determined by identifying areas of highest reconstruction loss. Finally, superpixel segmentation is performed to segment those regions. We show the proposed system is able to segment various sized and abstract tumours and achieves a mean and standard deviation Dice score of 0.771 and 0.176, respectively., Comment: 5 pages, 6 figures

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations. This has led to an increased attention on integrating state representation learning (SRL) techniques into the RL pipeline. Work in this field demonstrates a substantial improvement in sample efficiency among other benefits. However, to take full advantage of this paradigm, the quality of samples used for training plays a crucial role. More importantly, the diversity of these samples could affect the sample efficiency of vision-based RL, but also its generalization capability. In this work, we present an approach to improve the sample diversity. Our method enhances the exploration capability of the RL algorithms by taking advantage of the SRL setup. Our experiments show that the presented approach outperforms the baseline for all tested environments. These results are most apparent for environments where the baseline method struggles. Even in simple environments, our method stabilizes the training, reduces the reward variance and boosts sample efficiency., Comment: ICRA workshop on Curious Robots 2021

Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how humans learn. We introduce a setup in which an artificial agent first learns in a simulated world through self-supervised exploration. Following this, the representations learned through interaction with the world can be used to associate semantic concepts such as different types of doors. To do this, we use a method we call fast concept mapping which uses correlated firing patterns of neurons to define and detect semantic concepts. This association works instantaneous with very few labeled examples, similar to what we observe in humans in a phenomenon called fast mapping. Strikingly, this method already identifies objects with as little as one labeled example which highlights the quality of the encoding learned self-supervised through embodiment using curiosity-driven exploration. It therefor presents a feasible strategy for learning concepts without much supervision and shows that through pure interaction with the world meaningful representations of an environment can be learned., Comment: 10 pages. Find associated code and data here: https://github.com/vkakerbeck/FastConceptMapping

Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversity, and architectural restrictions. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches. These techniques are compared and contrasted, explaining the premises behind each and how they are interrelated, while reviewing current state-of-the-art advances and implementations., Comment: 20 pages, 9 figures, will appear in IEEE Transactions on Pattern Analysis and Machine Intelligence

Earth observation offers new insight into anthropogenic changes to nature, and how these changes are effecting (and are effected by) the built environment and the real economy. With the global availability of medium-resolution (10-30m) synthetic aperture radar (SAR) Sentinel-1 and multispectral Sentinel-2 imagery, machine learning can be employed to offer these insights at scale, unbiased to the reporting of companies and countries. In this paper, I introduce DeepSentinel, a data pipeline and experimentation framework for producing general-purpose semantic embeddings of paired Sentinel-1 and Sentinel-2 imagery. I document the development of an extensible corpus of labelled and unlabelled imagery for the purposes of sensor fusion research. With this new dataset I develop a set of experiments applying popular self-supervision methods and encoder architectures to a land cover classification problem. Tile2vec spatial encoding with a self-attention enabled ResNet model outperforms deeper ResNet variants as well as pretraining with variational autoencoding and contrastive loss. All supporting and derived data and code are made publicly available., Comment: Proposal presented at NeurIPS 2020 Climate Change AI Workshop and ESA Phi-Week. Copernicus Masters finalist. 14 pages; 4 figures

International audience; There has been an increasing interest in spiking neural networks in recent years. SNNs are seen as hypothetical solutions for the bottlenecks of ANNs in pattern recognition, such as energy efficiency. But current methods such as ANN-to-SNN conversion and back-propagation do not take full advantage of these networks, and unsupervised methods have not yet reached a success comparable to advanced artificial neural networks. It is important to study the behavior of SNNs trained with unsupervised learning methods such as spiketiming dependent plasticity (STDP) on video classification tasks, including mechanisms to model motion information using spikes, as this information is critical for video understanding. This paper presents multiple methods of transposing temporal information into a static format, and then transforming the visual information into spikes using latency coding. These methods are paired with two types of temporal fusion known as early and late fusion, and are used to help the spiking neural network in capturing the spatio-temporal features from videos. In this paper, we rely on the network architecture of a convolutional spiking neural network trained with STDP, and we test the performance of this network when challenged with action recognition tasks. Understanding how a spiking neural network responds to different methods of movement extraction and representation can help reduce the performance gap between SNNs and ANNs. In this paper we show the effect of the similarity in the shape and speed of certain actions on action recognition with spiking neural networks, we also highlight the effectiveness of some methods compared to others.

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image observations. This has led to increased attention on integrating state representation learning (SRL) techniques into the RL pipeline. Work in this field demonstrates a substantial improvement in sample efficiency among other benefits. However, to take full advantage of this paradigm, the quality of samples used for training plays a crucial role. More importantly, the diversity of these samples could affect the sample efficiency of vision-based RL, but also its generalization capability. In this work, we present an approach to improve sample diversity for state representation learning. Our method enhances the exploration capability of RL algorithms, by taking advantage of the SRL setup. Our experiments show that our proposed approach boosts the visitation of problematic states, improves the learned state representation, and outperforms the baselines for all tested environments. These results are most apparent for environments where the baseline methods struggle. Even in simple environments, our method stabilizes the training, reduces the reward variance, and promotes sample efficiency., Comment: arXiv admin note: substantial text overlap with arXiv:2109.13588

Preserving privacy is a growing concern in our society where sensors and cameras are ubiquitous. In this work, for the first time, we propose a trainable image acquisition method that removes the sensitive identity revealing information in the optical domain before it reaches the image sensor. The method benefits from a trainable optical convolution kernel which transmits the desired information while filters out the sensitive content. As the sensitive content is suppressed before it reaches the image sensor, it does not enter the digital domain therefore is unretrievable by any sort of privacy attack. This is in contrast with the current digital privacy-preserving methods that are all vulnerable to direct access attack. Also, in contrast with the previous optical privacy-preserving methods that cannot be trained, our method is data-driven and optimized for the specific application at hand. Moreover, there is no additional computation, memory, or power burden on the acquisition system since this processing happens passively in the optical domain and can even be used together and on top of the fully digital privacy-preserving systems. The proposed approach is adaptable to different digital neural networks and content. We demonstrate it for several scenarios such as smile detection as the desired attribute while the gender is filtered out as the sensitive content. We trained the optical kernel in conjunction with two adversarial neural networks where the analysis network tries to detect the desired attribute and the adversarial network tries to detect the sensitive content. We show that this method can reduce 65.1% of sensitive content when it is selected to be the gender and it only loses 7.3% of the desired content. Moreover, we reconstruct the original faces using the deep reconstruction method that confirms the ineffectiveness of reconstruction attacks to obtain the sensitive content., Comment: 9 pages, 9 figures

Face recognition in unconstrained environments is challenging due to variations in illumination, quality of sensing, motion blur and etc. An individual's face appearance can vary drastically under different conditions creating a gap between train (source) and varying test (target) data. The domain gap could cause decreased performance levels in direct knowledge transfer from source to target. Despite fine-tuning with domain specific data could be an effective solution, collecting and annotating data for all domains is extremely expensive. To this end, we propose a self-supervised domain learning (SSDL) scheme that trains on triplets mined from unlabelled data. A key factor in effective discriminative learning, is selecting informative triplets. Building on most confident predictions, we follow an "easy-to-hard" scheme of alternate triplet mining and self-learning. Comprehensive experiments on four different benchmarks show that SSDL generalizes well on different domains.

In this paper, we address the problem of vision-based obstacle avoidance for robotic manipulators. This topic poses challenges for both perception and motion generation. While most work in the field aims at improving one of those aspects, we provide a unified framework for approaching this problem. The main goal of this framework is to connect perception and motion by identifying the relationship between the visual input and the corresponding motion representation. To this end, we propose a method for learning reactive obstacle avoidance policies. We evaluate our method on goal-reaching tasks for single and multiple obstacles scenarios. We show the ability of the proposed method to efficiently learn stable obstacle avoidance strategies at a high success rate, while maintaining closed-loop responsiveness required for critical applications like human-robot interaction., Accepted for publication at CoRL 2020

An automatic image segmentation procedure is an inevitable part of many image analyses and computer vision which deeply affect the rest of the system; therefore, a set of interactive segmentation evaluation methods can substantially simplify the system development process. This entry presents the state of the art of quantitative evaluation metrics for color image segmentation methods by performing an analytical and comparative review of the measures. The decision-making process in selecting a suitable evaluation metric is still very serious because each metric tends to favor a different segmentation method for each benchmark dataset. Furthermore, a conceptual comparison of these metrics is provided at a high level of abstraction and is discussed for understanding the quantitative changes in different image segmentation results., 19 pages, 11 figures, 6 tables, 29 equations, book chapter, 2 authors

An important challenge in metric learning is scalability to both size and dimension of input data. Online metric learning algorithms are proposed to address this challenge. Existing methods are commonly based on (Passive Aggressive) PA approach. Hence, they can rapidly process large volumes of data with an adaptive learning rate. However, these algorithms are based on the Hinge loss and so are not robust against outliers and label noise. Also, existing online methods usually assume training triplets or pairwise constraints are exist in advance. However, many datasets in real-world applications are in the form of input data and their associated labels. We address these challenges by formulating the online Distance-Similarity learning problem with the robust Rescaled hinge loss function. The proposed model is rather general and can be applied to any PA-based online Distance-Similarity algorithm. Also, we develop an efficient robust one-pass triplet construction algorithm. Finally, to provide scalability in high dimensional DML environments, the low-rank version of the proposed methods is presented that not only reduces the computational cost significantly but also keeps the predictive performance of the learned metrics. Also, it provides a straightforward extension of our methods for deep Distance-Similarity learning. We conduct several experiments on datasets from various applications. The results confirm that the proposed methods significantly outperform state-of-the-art online DML methods in the presence of label noise and outliers by a large margin., An Online Distance-Similarity learning approach in noisy environment

This paper proposes a new type of generative model that is able to quickly learn a latent representation without an encoder. This is achieved using empirical Bayes to calculate the expectation of the posterior, which is implemented by initialising a latent vector with zeros, then using the gradient of the log-likelihood of the data with respect to this zero vector as new latent points. The approach has similar characteristics to autoencoders, but with a simpler architecture, and is demonstrated in a variational autoencoder equivalent that permits sampling. This also allows implicit representation networks to learn a space of implicit functions without requiring a hypernetwork, retaining their representation advantages across datasets. The experiments show that the proposed method converges faster, with significantly lower reconstruction error than autoencoders, while requiring half the parameters., 16 pages, 17 figures, accepted at ICLR 2021, camera-ready version

Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures. An exciting algorithm denoted as Restricted Boltzmann Machine relies on energy- and probabilistic-based nature to tackle the most diverse applications, such as classification, reconstruction, and generation of images and signals. Nevertheless, one can see they are not adequately renowned compared to other well-known deep learning techniques, e.g., Convolutional Neural Networks. Such behavior promotes the lack of researches and implementations around the literature, coping with the challenge of sufficiently comprehending these energy-based systems. Therefore, in this paper, we propose a Python-inspired framework in the context of energy-based architectures, denoted as Learnergy. Essentially, Learnergy is built upon PyTorch to provide a more friendly environment and a faster prototyping workspace and possibly the usage of CUDA computations, speeding up their computational time., 12 pages, 12 figures

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are not comparable. In this work, we introduce an end-to-end deep multimodal convolutional-recurrent network for learning both vision and language representations simultaneously to infer image-text similarity. The model learns which pairs are a match (positive) and which ones are a mismatch (negative) using a hinge-based triplet ranking. To learn about the joint representations, we leverage our newly extracted collection of tweets from Twitter. The main characteristic of our dataset is that the images and tweets are not standardized the same as the benchmarks. Furthermore, there can be a higher semantic correlation between the pictures and tweets contrary to benchmarks in which the descriptions are well-organized. Experimental results on MS-COCO benchmark dataset show that our model outperforms certain methods presented previously and has competitive performance compared to the state-of-the-art. The code and dataset have been made available publicly., 6 pages and 2 figures, Learn more about this project at https://iasbs.ac.ir/~ansari/deeptwitter

Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, and image segmentation. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, and Bayesian classifiers, might lack complexity and diversity, not suitable when dealing with real-world data. A recent graph-inspired classifier, known as the Optimum-Path Forest, has proven to be a state-of-the-art technique, comparable to Support Vector Machines and even surpassing it in some tasks. This paper proposes a Python-based Optimum-Path Forest framework, denoted as OPFython, where all of its functions and classes are based upon the original C language implementation. Additionally, as OPFython is a Python-based library, it provides a more friendly environment and a faster prototyping workspace than the C language., 14 pages, 11 figures

Deep learning technology has enabled successful modeling of complex facial features when high quality images are available. Nonetheless, accurate modeling and recognition of human faces in real world scenarios `on the wild' or under adverse conditions remains an open problem. When unconstrained faces are mapped into deep features, variations such as illumination, pose, occlusion, etc., can create inconsistencies in the resultant feature space. Hence, deriving conclusions based on direct associations could lead to degraded performance. This rises the requirement for a basic feature space analysis prior to face recognition. This paper devises a joint clustering and classification scheme which learns deep face associations in an easy-to-hard way. Our method is based on hierarchical clustering where the early iterations tend to preserve high reliability. The rationale of our method is that a reliable clustering result can provide insights on the distribution of the feature space, that can guide the classification that follows. Experimental evaluations on three tasks, face verification, face identification and rank-order search, demonstrates better or competitive performance compared to the state-of-the-art, on all three experiments.

Recent advances in the interdisciplinary scientific field of machine perception, computer vision, and biomedical engineering underpin a collection of machine learning algorithms with a remarkable ability to decipher the contents of microscope and nanoscope images. Machine learning algorithms are transforming the interpretation and analysis of microscope and nanoscope imaging data through use in conjunction with biological imaging modalities. These advances are enabling researchers to carry out real-time experiments that were previously thought to be computationally impossible. Here we adapt the theory of survival of the fittest in the field of computer vision and machine perception to introduce a new framework of multi-class instance segmentation deep learning, Darwin's Neural Network (DNN), to carry out morphometric analysis and classification of COVID19 and MERS-CoV collected in vivo and of multiple mammalian cell types in vitro., Comment: 19 pages, 7 figures

We consider problems of dimensionality reduction and learning data representations for continuous spaces with two or more independent degrees of freedom. Such problems occur, for example, when observing shapes with several components that move independently. Mathematically, if the parameter space of each continuous independent motion is a manifold, then their combination is known as a product manifold. In this paper, we present a new paradigm for non-linear independent component analysis called manifold factorization. Our factorization algorithm is based on spectral graph methods for manifold learning and the separability of the Laplacian operator on product spaces. Recovering the factors of a manifold yields meaningful lower-dimensional representations and provides a new way to focus on particular aspects of the data space while ignoring others. We demonstrate the potential use of our method for an important and challenging problem in structural biology: mapping the motions of proteins and other large molecules using cryo-electron microscopy datasets., Comment: 10 pages, 4 figures

We present an algorithm for multi-scale tumor (chimeric cell) detection in high resolution slide scans. The broad range of tumor sizes in our dataset pose a challenge for current Convolutional Neural Networks (CNN) which often fail when image features are very small (8 pixels). Our approach modifies the effective receptive field at different layers in a CNN so that objects with a broad range of varying scales can be detected in a single forward pass. We define rules for computing adaptive prior anchor boxes which we show are solvable under the equal proportion interval principle. Two mechanisms in our CNN architecture alleviate the effects of non-discriminative features prevalent in our data - a foveal detection algorithm that incorporates a cascade residual-inception module and a deconvolution module with additional context information. When integrated into a Single Shot MultiBox Detector (SSD), these additions permit more accurate detection of small-scale objects. The results permit efficient real-time analysis of medical images in pathology and related biomedical research fields., Comment: 14 pages, 7 figures, 2 tables

In this paper, a smile and laugh facial expression is presented based on dimension reduction and description process of the key points. The paper has two main objectives; the first is to extract the local critical points in terms of their apparent features, and the second is to reduce the system's dependence on training inputs. To achieve these objectives, three different scenarios on extracting the features are proposed. First of all, the discrete parts of a face are detected by local binary pattern method that is used to extract a set of global feature vectors for texture classification considering various regions of an input-image face. Then, in the first scenario and with respect to the correlation changes of adjacent pixels on the texture of a mouth area, a set of local key points are extracted using the Harris corner detector. In the second scenario, the dimension reduction of the extracted points of first scenario provided by principal component analysis algorithm leading to reduction in computational costs and overall complexity without loss of performance and flexibility, etc., 20 pages, in Farsi, 11 figures, 7 tables, 21 equations, journal, 2 authors

In the authors' opinion, anomaly detection systems, or ADS, seem to be the most perspective direction in the subject of attack detection, because these systems can detect, among others, the unknown (zero-day) attacks. To detect anomalies, the authors propose to use machine synesthesia. In this case, machine synesthesia is understood as an interface that allows using image classification algorithms in the problem of detecting network anomalies, making it possible to use non-specialized image detection methods that have recently been widely and actively developed. The proposed approach is that the network traffic data is "projected" into the image. It can be seen from the experimental results that the proposed method for detecting anomalies shows high results in the detection of attacks. On a large sample, the value of the complex efficiency indicator reaches 97%., Comment: 12 pages, 2 figures, 5 tables. Accepted to the Intelligent Systems Conference (IntelliSys) 2019

In this note we discuss a common misconception, namely that embeddings are always used to reduce the dimensionality of the item space. We show that when we measure dimensionality in terms of information entropy then the embedding of sparse probability distributions, that can be used to represent sparse features or data, may or not reduce the dimensionality of the item space. However, the embeddings do provide a different and often more meaningful representation of the items for a particular task at hand. Also, we give upper bounds and more precise guidelines for choosing the embedding dimension., Comment: 8 pages, 2 figures

Deep learning models have been successfully used in computer vision and many other fields. We propose an unorthodox algorithm for performing quantization of the model parameters. In contrast with popular quantization schemes based on thresholds, we use a novel technique based on periodic functions, such as continuous trigonometric sine or cosine as well as non-continuous hat functions. We apply these functions component-wise and add the sum over the model parameters as a regularizer to the model loss during training. The frequency and amplitude hyper-parameters of these functions can be adjusted during training. The regularization pushes the weights into discrete points that can be encoded as integers. We show that using this technique the resulting quantized models exhibit the same accuracy as the original ones on CIFAR-10 and ImageNet datasets., 11 pages, 7 figures

Sparse representation of structured signals requires modelling strategies that maintain specific signal properties, in addition to preserving original information content and achieving simpler signal representation. Therefore, the major design challenge is to introduce adequate problem formulations and offer solutions that will efficiently lead to desired representations. In this context, sparse representation of covariance and precision matrices, which appear as feature descriptors or mixture model parameters, respectively, will be in the main focus of this paper., 8 pages

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer more parallelism and hence better computational efficiency. We have developed a new training approach that, rather than statically choosing a single batch size for all epochs, adaptively increases the batch size during the training process. Our method delivers the convergence rate of small batch sizes while achieving performance similar to large batch sizes. We analyse our approach using the standard AlexNet, ResNet, and VGG networks operating on the popular CIFAR-10, CIFAR-100, and ImageNet datasets. Our results demonstrate that learning with adaptive batch sizes can improve performance by factors of up to 6.25 on 4 NVIDIA Tesla P100 GPUs while changing accuracy by less than 1% relative to training with fixed batch sizes., 14 pages

In this paper, we propose a novel learning based method for automated segmenta-tion of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton fea-tures are used to classify the MRI image voxels. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI train-ing dataset using the FCN. The learned features are then applied to random for-ests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 challenge dataset. The results show that the application of the random forest classifier to multimodal MRI images using machine-learned features based on FCN and hand-designed features based on textons provides promising segmentations. The Dice overlap measure for automatic brain tumor segmentation against ground truth is 0.88, 080 and 0.73 for complete tumor, core and enhancing tumor, respectively.

In this paper, a model for classification of logos based on symbolic representation of features is presented. The proposed model makes use of global features of logo images such as color, texture, and shape features for classification. The logo images are broadly classified into three different classes, viz., logo image containing only text, an image with only symbol, and an image with both text and a symbol. In each class, the similar looking logo images are clustered using K-means clustering algorithm. The intra-cluster variations present in each cluster corresponding to each class are then preserved using symbolic interval data. Thus referenced logo images are represented in the form of interval data. A sample logo image is then classified using suitable symbolic classifier. For experimentation purpose, relatively large amount of color logo images is created consisting of 5044 logo images. The classification results are validated with the help of accuracy, precision, recall, F-measure, and time. To check the efficacy of the proposed model, the comparative analyses are given against the other models. The results show that the proposed model outperforms the other models with respect to time and F-measure., Comment: 15 pages, 6 figures, 6 tables, Proceedings of International Conference on Computer Vision and Image Processing (CVIP 2016). arXiv admin note: text overlap with arXiv:1609.01414

In this paper, a new method is proposed for sparse PCA based on the recursive divide-and-conquer methodology. The main idea is to separate the original sparse PCA problem into a series of much simpler sub-problems, each having a closed-form solution. By recursively solving these sub-problems in an analytical way, an efficient algorithm is constructed to solve the sparse PCA problem. The algorithm only involves simple computations and is thus easy to implement. The proposed method can also be very easily extended to other sparse PCA problems with certain constraints, such as the nonnegative sparse PCA problem. Furthermore, we have shown that the proposed algorithm converges to a stationary point of the problem, and its computational complexity is approximately linear in both data size and dimensionality. The effectiveness of the proposed method is substantiated by extensive experiments implemented on a series of synthetic and real data in both reconstruction-error-minimization and data-variance-maximization viewpoints., 35 pages, 4 figures

We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image analysis and is at heart of most graphic recognition systems. Our method uses structural approach for symbol representation and statistical classifier for symbol recognition. In our system we represent symbols by their graph based signatures: a graphic symbol is vectorized and is converted to an attributed relational graph, which is used for computing a feature vector for the symbol. This signature corresponds to geometry and topology of the symbol. We learn a Bayesian network to encode joint probability distribution of symbol signatures and use it in a supervised learning scenario for graphic symbol recognition. We have evaluated our method on synthetically deformed and degraded images of pre-segmented 2D architectural and electronic symbols from GREC databases and have obtained encouraging recognition rates., 5 pages, 8 figures, Tenth International Conference on Document Analysis and Recognition (ICDAR), IEEE Computer Society, 2009, volume 10, 1325-1329

Medical Informatics and the application of modern signal processing in the assistance of the diagnostic process in medical imaging is one of the more recent and active research areas today. This thesis addresses a variety of issues related to the general problem of medical image analysis, specifically in mammography, and presents a series of algorithms and design approaches for all the intermediate levels of a modern system for computer-aided diagnosis (CAD). The diagnostic problem is analyzed with a systematic approach, first defining the imaging characteristics and features that are relevant to probable pathology in mammo-grams. Next, these features are quantified and fused into new, integrated radio-logical systems that exhibit embedded digital signal processing, in order to improve the final result and minimize the radiological dose for the patient. In a higher level, special algorithms are designed for detecting and encoding these clinically interest-ing imaging features, in order to be used as input to advanced pattern classifiers and machine learning models. Finally, these approaches are extended in multi-classifier models under the scope of Game Theory and optimum collective deci-sion, in order to produce efficient solutions for combining classifiers with minimum computational costs for advanced diagnostic systems. The material covered in this thesis is related to a total of 18 published papers, 6 in scientific journals and 12 in international conferences., PhD thesis summary, 12 pages

We consider the design of a pattern recognition that matches templates to images, both of which are spatially sampled and encoded as temporal sequences. The image is subject to a combination of various perturbations. These include ones that can be modeled as parameterized uncertainties such as image blur, luminance, translation, and rotation as well as unmodeled ones. Biological and neural systems require that these perturbations be processed through a minimal number of channels by simple adaptation mechanisms. We found that the most suitable mathematical framework to meet this requirement is that of weakly attracting sets. This framework provides us with a normative and unifying solution to the pattern recognition problem. We analyze the consequences of its explicit implementation in neural systems. Several properties inherent to the systems designed in accordance with our normative mathematical argument coincide with known empirical facts. This is illustrated in mental rotation, visual search and blur/intensity adaptation. We demonstrate how our results can be applied to a range of practical problems in template matching and pattern recognition., 52 pages, 12 figures

Despite encouraging recent progresses in ensemble approaches, classification methods seem to have reached a plateau in development. Further advances depend on a better understanding of geometrical and topological characteristics of point sets in high-dimensional spaces, the preservation of such characteristics under feature transformations and sampling processes, and their interaction with geometrical models used in classifiers. We discuss an attempt to measure such properties from data sets and relate them to classifier accuracies., Proceedings of the 7th Course on Ensemble Methods for Learning Machines at the International School on Neural Nets ``E.R. Caianiello''

Studies on ensemble methods for classification suffer from the difficulty of modeling the complementary strengths of the components. Kleinberg's theory of stochastic discrimination (SD) addresses this rigorously via mathematical notions of enrichment, uniformity, and projectability of an ensemble. We explain these concepts via a very simple numerical example that captures the basic principles of the SD theory and method. We focus on a fundamental symmetry in point set covering that is the key observation leading to the foundation of the theory. We believe a better understanding of the SD method will lead to developments of better tools for analyzing other ensemble methods., Comment: Proceedings of the 7th Course on Ensemble Methods for Learning Machines at the International School on Neural Nets ``E.R. Caianiello''