Search

Genomic prediction, which is based on solving linear mixed-model (LMM) equations, is the most popular method for predicting breeding values or phenotypic performance for economic traits in livestock. With the need to further improve the performance of genomic prediction, nonlinear methods have been considered as an alternative and promising approach. The excellent ability to predict phenotypes in animal husbandry has been demonstrated by machine learning (ML) approaches, which have been rapidly developed. To investigate the feasibility and reliability of implementing genomic prediction using nonlinear models, the performances of genomic predictions for pig productive traits using the linear genomic selection model and nonlinear machine learning models were compared. Then, to reduce the high-dimensional features of genome sequence data, different machine learning algorithms, including the random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost) and convolutional neural network (CNN) algorithms, were used to perform genomic feature selection as well as genomic prediction on reduced feature genome data. All of the analyses were processed on two real pig datasets: the published PIC pig dataset and a dataset comprising data from a national pig nucleus herd in Chifeng, North China. Overall, the accuracies of predicted phenotypic performance for traits T1, T2, T3 and T5 in the PIC dataset and average daily gain (ADG) in the Chifeng dataset were higher using the ML methods than the LMM method, while those for trait T4 in the PIC dataset and total number of piglets born (TNB) in the Chifeng dataset were slightly lower using the ML methods than the LMM method. Among all the different ML algorithms, SVM was the most appropriate for genomic prediction. For the genomic feature selection experiment, the most stable and most accurate results across different algorithms were achieved using XGBoost in combination with the SVM algorithm. Through feature selection, the number of genomic markers can be reduced to 1 in 20, while the predictive performance on some traits can even be improved compared to using the full genome data. Finally, we developed a new tool that can be used to execute combined XGBoost and SVM algorithms to realize genomic feature selection and phenotypic prediction., (© 2023 Federation of American Societies for Experimental Biology.)

IntroductionThe diagnosis and treatment of ankylosing spondylitis (AS) is a difficult task, especially in less developed countries without access to experts. To address this issue, a comprehensive artificial intelligence (AI) tool was created to help diagnose and predict the course of AS.MethodsIn this retrospective study, a dataset of 5389 pelvic radiographs (PXRs) from patients treated at a single medical center between March 2014 and April 2022 was used to create an ensemble deep learning (DL) model for diagnosing AS. The model was then tested on an additional 583 images from three other medical centers, and its performance was evaluated using the area under the receiver operating characteristic curve analysis, accuracy, precision, recall, and F1 scores. Furthermore, clinical prediction models for identifying high-risk patients and triaging patients were developed and validated using clinical data from 356 patients.ResultsThe ensemble DL model demonstrated impressive performance in a multicenter external test set, with precision, recall, and area under the receiver operating characteristic curve values of 0.90, 0.89, and 0.96, respectively. This performance surpassed that of human experts, and the model also significantly improved the experts' diagnostic accuracy. Furthermore, the model's diagnosis results based on smartphone-captured images were comparable to those of human experts. Additionally, a clinical prediction model was established that accurately categorizes patients with AS into high-and low-risk groups with distinct clinical trajectories. This provides a strong foundation for individualized care.DiscussionIn this study, an exceptionally comprehensive AI tool was developed for the diagnosis and management of AS in complex clinical scenarios, especially in underdeveloped or rural areas that lack access to experts. This tool is highly beneficial in providing an efficient and effective system of diagnosis and management.

Neural networks do not generalize well to unseen data with domain shifts—a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simple plug-and-play, parameter-free module that can improve domain generalization performance without the need to collect more data or increase model capacity. The design of MixStyle is simple: it mixes the feature statistics of two random instances in a single forward pass during training. The idea is grounded by the finding from recent style transfer research that feature statistics capture image style information, which essentially defines visual domains. Therefore, mixing feature statistics can be seen as an efficient way to synthesize new domains in the feature space, thus achieving data augmentation. MixStyle is easy to implement with a few lines of code, does not require modification to training objectives, and can fit a variety of learning paradigms including supervised domain generalization, semi-supervised domain generalization, and unsupervised domain adaptation. Our experiments show that MixStyle can significantly boost out-of-distribution generalization performance across a wide range of tasks including image recognition, instance retrieval and reinforcement learning. The source code is released at https://github.com/KaiyangZhou/mixstyle-release. [ABSTRACT FROM AUTHOR]

Machine learning makes multimedia data (e.g., images) more attractive, however, multimedia data is usually distributed and privacy sensitive. Multiple distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model without requiring to share their private samples with any third-party entities. In this paper, we show that FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack, in which a malicious client (i.e., adversary) can reconstruct samples with the same distribution as the training samples from other clients (i.e., victims). Since a benign client's data can be leaked to the adversary, this attack brings the risk of local data leakage for clients in many security-critical FL applications. Thus, we propose Fed-EDKD (i.e., Federated Ensemble Data-free Knowledge Distillation) technique to improve the current popular FL schemes to resist C-GANs attack. In Fed-EDKD, each client submits a local model to the server for obtaining an ensemble global model. Then, to avoid model expansion, Fed-EDKD adopts data-free knowledge distillation techniques to transfer knowledge from the ensemble global model to a compressed model. By this way, Fed-EDKD reduces the adversary's control capability over the global model, so Fed-EDKD can effectively mitigate C-GANs attack. Finally, the experimental results demonstrate that Fed-EDKD significantly mitigates C-GANs attack while only incurring a slight accuracy degradation of FL. [ABSTRACT FROM AUTHOR]

As various research fields continue to evolve, new technologies emerge constantly, making it challenging for scholars to keep up with the latest and most promising research directions. To address this issue, we propose TrendFlow, a framework that leverages machine learning and deep learning techniques for analyzing research trends. TrendFlow first searches relevant literature based on user-defined queries, then clusters the searched literature according to the abstracts, and finally generates keyphrases of the abstracts as research trends for each cluster. Our experimental results highlight the superior performance of TrendFlow compared to traditional literature analysis tools. We have released the beta version of TrendFlow on Huggingface. [ABSTRACT FROM AUTHOR]

The problem of fine-grained sketch-based image retrieval (FG-SBIR) is defined and investigated in this paper. In FG-SBIR, free-hand human sketch images are used as queries to retrieve photo images containing the same object instances. It is thus a cross-domain (sketch to photo) instance-level retrieval task. It is an extremely challenging problem because (i) visual comparisons and matching need to be executed under large domain gap, i.e., from black and white line drawing sketches to colour photos; (ii) it requires to capture the fine-grained (dis)similarities of sketches and photo images while free-hand sketches drawn by different people present different levels of deformation and expressive interpretation; and (iii) annotated cross-domain fine-grained SBIR datasets are scarce, challenging many state-of-the-art machine learning techniques, particularly those based on deep learning. In this paper, for the first time, we address all these challenges, providing a step towards the capabilities that would underpin a commercial sketch-based object instance retrieval application. Specifically, a new large-scale FG-SBIR database is introduced which is carefully designed to reflect the real-world application scenarios. A deep cross-domain matching model is then formulated to solve the intrinsic drawing style variability, large domain gap issues, and capture instance-level discriminative features. It distinguishes itself by a carefully designed attention module. Extensive experiments on the new dataset demonstrate the effectiveness of the proposed model and validate the need for a rigorous definition of the FG-SBIR problem and collecting suitable datasets. [ABSTRACT FROM AUTHOR]

During the past decade, both multi-label learning and zero-shot learning have attracted huge research attention, and significant progress has been made. Multi-label learning algorithms aim to predict multiple labels given one instance, while most existing zero-shot learning approaches target at predicting a single testing label for each unseen class via transferring knowledge from auxiliary seen classes to target unseen classes. However, relatively less effort has been made on predicting multiple labels in the zero-shot setting, which is nevertheless a quite challenging task. In this work, we investigate and formalize a flexible framework consisting of two components, i.e., visual-semantic embedding and zero-shot multi-label prediction. First, we present a deep regression model to project the visual features into the semantic space, which explicitly exploits the correlations in the intermediate semantic layer of word vectors and makes label prediction possible. Then, we formulate the label prediction problem as a pairwise one and employ Ranking SVM to seek the unique multi-label correlations in the embedding space. Furthermore, we provide a transductive multi-label zero-shot prediction approach that exploits the testing data manifold structure. We demonstrate the effectiveness of the proposed approach on three popular multi-label datasets with state-of-the-art performance obtained on both conventional and generalized ZSL settings. [ABSTRACT FROM AUTHOR]

Person re-identification (re-id) aims to match people across non-overlapping camera views in a public space. This is a challenging problem because the people captured in surveillance videos often wear similar clothing. Consequently, the differences in their appearance are typically subtle and only detectable at particular locations and scales. In this paper, we propose a deep re-id network (MuDeep) that is composed of two novel types of layers – a multi-scale deep learning layer, and a leader-based attention learning layer. Specifically, the former learns deep discriminative feature representations at different scales, while the latter utilizes the information from multiple scales to lead and determine the optimal weightings for each scale. The importance of different spatial locations for extracting discriminative features is learned explicitly via our leader-based attention learning layer. Extensive experiments are carried out to demonstrate that the proposed MuDeep outperforms the state-of-the-art on a number of benchmarks and has a better generalization ability under a domain generalization setting. [ABSTRACT FROM AUTHOR]

Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size, and Inadaptability over time. In this work, we present a unified solution to address both problems. Specifically, we propose to construct an identity regression space (IRS) based on embedding different training person identities (classes) and formulate re-id as a regression problem solved by identity regression in the IRS. The IRS approach is characterised by a closed-form solution with high learning efficiency and an inherent incremental learning capability with human-in-the-loop. Extensive experiments on four benchmarking datasets (VIPeR, CUHK01, CUHK03 and Market-1501) show that the IRS model not only outperforms state-of-the-art re-id methods, but also is more scalable to large re-id population size by rapidly updating model and actively selecting informative samples with reduced human labelling effort. [ABSTRACT FROM AUTHOR]

A number of vision problems such as zero-shot learning and person re-identification can be considered as cross-class transfer learning problems. As mid-level semantic properties shared cross different object classes, attributes have been studied extensively for knowledge transfer across classes. Most previous attribute learning methods focus only on human-defined/nameable semantic attributes, whilst ignoring the fact there also exist undefined/latent shareable visual properties, or latent attributes. These latent attributes can be either discriminative or non-discriminative parts depending on whether they can contribute to an object recognition task. In this work, we argue that learning the latent attributes jointly with user-defined semantic attributes not only leads to better representation but also helps semantic attribute prediction. A novel dictionary learning model is proposed which decomposes the dictionary space into three parts corresponding to semantic, latent discriminative and latent background attributes respectively. Such a joint attribute learning model is then extended by following a multi-task transfer learning framework to address a more challenging unsupervised domain adaptation problem, where annotations are only available on an auxiliary dataset and the target dataset is completely unlabelled. Extensive experiments show that the proposed models, though being linear and thus extremely efficient to compute, produce state-of-the-art results on both zero-shot learning and person re-identification. [ABSTRACT FROM AUTHOR]

With the recent renaissance of deep convolutional neural networks (CNNs), encouraging breakthroughs have been achieved on the supervised recognition tasks, where each class has sufficient and fully annotated training data. However, to scale the recognition to a large number of classes with few or no training samples for each class remains an unsolved problem. One approach is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/learning. This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, data sets, and evaluation settings. We also overview related recognition tasks including one-shot and open-set recognition, which can be used as natural extensions of zero-shot recognition when a limited number of class samples become available or when zero-shot recognition is implemented in a real-world setting. We highlight the limitations of existing approaches and point out future research directions in this existing new research area. [ABSTRACT FROM PUBLISHER]

A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these ‘free’ tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel $L_1$ -optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the $L_1$ -optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields state-of-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy. [ABSTRACT FROM PUBLISHER]

Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks. [ABSTRACT FROM PUBLISHER]

Gait is a useful biometric because it can operate from a distance and without subject cooperation. However, it is affected by changes in covariate conditions (carrying, clothing, view angle, etc.). Existing methods suffer from lack of training samples, can only cope with changes in a subset of conditions with limited success, and implicitly assume subject cooperation. We propose a novel approach which casts gait recognition as a bipartite ranking problem and leverages training samples from different people and even from different datasets. By exploiting learning to rank, the problem of model over-fitting caused by under-sampled training data is effectively addressed. This makes our approach suitable under a genuine uncooperative setting and robust against changes in any covariate conditions. Extensive experiments demonstrate that our approach drastically outperforms existing methods, achieving up to 14-fold increase in recognition rate under the most difficult uncooperative settings. [ABSTRACT FROM AUTHOR]

Discovering rare categories and classifying new instances of them are important data mining issues in many fields, but fully supervised learning of a rare class classifier is prohibitively costly in labeling effort. There has therefore been increasing interest both in active discovery: to identify new classes quickly, and active learning: to train classifiers with minimal supervision. These goals occur together in practice and are intrinsically related because examples of each class are required to train a classifier. Nevertheless, very few studies have tried to optimise them together, meaning that data mining for rare classes in new domains makes inefficient use of human supervision. Developing active learning algorithms to optimise both rare class discovery and classification simultaneously is challenging because discovery and classification have conflicting requirements in query criteria. In this paper, we address these issues with two contributions: a unified active learning model to jointly discover new categories and learn to classify them by adapting query criteria online; and a classifier combination algorithm that switches generative and discriminative classifiers as learning progresses. Extensive evaluation on a batch of standard UCI and vision data sets demonstrates the superiority of this approach over existing methods. [ABSTRACT FROM AUTHOR]

Abstract: The task of discovering natural groupings of input patterns, or clustering, is an important aspect of machine learning and pattern analysis. In this paper, we study the widely used spectral clustering algorithm which clusters data using eigenvectors of a similarity/affinity matrix derived from a data set. In particular, we aim to solve two critical issues in spectral clustering: (1) how to automatically determine the number of clusters, and (2) how to perform effective clustering given noisy and sparse data. An analysis of the characteristics of eigenspace is carried out which shows that (a) not every eigenvectors of a data affinity matrix is informative and relevant for clustering; (b) eigenvector selection is critical because using uninformative/irrelevant eigenvectors could lead to poor clustering results; and (c) the corresponding eigenvalues cannot be used for relevant eigenvector selection given a realistic data set. Motivated by the analysis, a novel spectral clustering algorithm is proposed which differs from previous approaches in that only informative/relevant eigenvectors are employed for determining the number of clusters and performing clustering. The key element of the proposed algorithm is a simple but effective relevance learning method which measures the relevance of an eigenvector according to how well it can separate the data set into different clusters. Our algorithm was evaluated using synthetic data sets as well as real-world data sets generated from two challenging visual learning problems. The results demonstrated that our algorithm is able to estimate the cluster number correctly and reveal natural grouping of the input data/patterns even given sparse and noisy data. [Copyright &y& Elsevier]

Summary: In the presence of scale, dynamism, uncertainty, and elasticity, cloud engineers face several challenges when allocating resources for cloud‐based software services. They should allocate appropriate resources in order to guarantee good quality of services as well as low cost of resources. Self‐adaptive ability is needed in this process because engineers' intervention is difficult. Traditional self‐adaptive resource allocation methods are policy‐driven. Thus, cloud engineers usually have to develop separate sets of rules for each systems in order to allocate resources effectively, which leads to high administrative cost and implementation complexity. Machine learning has made great achievements in many fields, and it can be also applied to resource allocation. In this paper, we present a self‐learning and self‐adaptive approach to resource allocation for cloud‐based software services. For a given cloud‐based software service, its QoS model is firstly trained on history data, which is capable to predict the QoS value as output by using the information on workload and allocated resources as inputs. Then, on‐line decision‐making on resource allocation can be carried out automatically based on genetic algorithm, which is aimed to search reasonable resource allocation plan by using the QoS model. We evaluate our approach on RUBiS benchmark, demonstrating the accuracy of the QoS model over 90% and the improvement of resource utilization by 10%‐30%. [ABSTRACT FROM AUTHOR]

One of the most interesting and desired capabilities for automated video behavior analysis is the identification of rarely occurring and subtle behaviors. This is of practical value because dangerous or illegal activities often have few or possibly only one prior example to learn from and are often subtle. Rare and subtle behavior learning is challenging for two reasons: 1) Contemporary modeling approaches require more data and supervision than may be available and 2) the most interesting and potentially critical rare behaviors are often visually subtle—occurring among more obvious typical behaviors or being defined by only small spatio-temporal deviations from typical behaviors. In this paper, we introduce a novel weakly supervised joint topic model which addresses these issues. Specifically, we introduce a multiclass topic model with partially shared latent structure and associated learning and inference algorithms. These contributions will permit modeling of behaviors from as few as one example, even without localization by the user and when occurring in clutter, and subsequent classification and localization of such behaviors online and in real time. We extensively validate our approach on two standard public-space data sets, where it clearly outperforms a batch of contemporary alternatives. [ABSTRACT FROM PUBLISHER]