查看更多>>摘要：The long-tailed distribution in the dataset is one of the major challenges of deep learning. Convolutional Neural Networks have poor performance in identifying classes with only a few samples. For this problem, it has been proved that separating the feature learning stage and the classifier learning stage improves the performance of models effectively, which is called decoupled learning. We use soft labels to improve the performance of the decoupled learning framework by proposing a Dynamic Auxiliary Soft Labels (DaSL) method. Specifically, we design a dedicated auxiliary network to generate auxiliary soft labels for the two different training stages. In the feature learning stage, it helps to learn features with smaller variance within the class, and in the classifier learning stage it helps to alleviate the overconfidence of the model prediction. We also introduce a feature-level distillation method for the feature learning, and improve the learning of general features through multi-scale feature fusion. We conduct extensive experiments on three long-tailed recognition benchmark datasets to demonstrate the effectiveness of our DaSL.(C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：This paper mainly focuses on the lag H(infinity & nbsp;)synchronization problem of coupled neural networks with multiple state or delayed state couplings. On one hand, by exploiting state feedback controller and Lyapunov functional, a criterion of lag H-infinity synchronization for coupled neural networks with multiple state couplings (CNNMSCs) is insured, and lag H-infinity synchronization problem in CNNMSCs is also coped with based on the adaptive state feedback controller. On the other hand, we explore the lag H-infinity synchronization for coupled neural networks with multiple delayed state couplings (CNNMDSCs) by utilizing similar control strategies. At last, two numerical examples are presented to verify the effectiveness and correctness of lag H-infinity synchronization for CNNMSCs and CNNMDSCs. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：A new design of a non-parametric adaptive approximate model based on Differential Neural Networks (DNNs) applied for a class of non-negative environmental systems with an uncertain mathematical model is the primary outcome of this study. The approximate model uses an extended state formulation that gathers the dynamics of the DNN and a state projector (pDNN). Implementing a non-differentiable projection operator ensures the positiveness of the identifier states. The extended form allows producing continuous dynamics for the projected model. The design of the learning laws for the weight adjustment of the continuous projected DNN considered the application of a controlled Lyapunov-like function. The stability analysis based on the proposed Lyapunov-like function leads to the characterization of the ultimate boundedness property for the identification error. Applying the Attractive Ellipsoid Method (AEM) yields to analyze the convergence quality of the designed approximate model. The solution to the specific optimization problem using the AEM with matrix inequalities constraints allows us to find the parameters of the considered DNN that minimizes the ultimate bound. The evaluation of two numerical examples confirmed the ability of the proposed pDNN to approximate the positive model in the presence of bounded noises and perturbations in the measured data. The first example corresponds to a catalytic ozonation system that can be used to decompose toxic and recalcitrant contaminants. The second one describes the bacteria growth in aerobic batch regime biodegrading simple organic matter mixture. (c) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：In the era of big data, there are an increasing number of multisource information data, and multi-view clustering (MVC) algorithms have developed rapidly. However, the affinity matrix learned by most MVC methods is not clean and precise enough and cannot describe the latent structure of multi-view data accurately, which results in poor clustering performance. In this paper, we propose a novel Double Structure Scaled Simplex Representation (DSSSR) method for MVC. Initially, we concatenate the multi-view data into a joint representation. Then, we use the scaled simplex representation (SSR) method on the concatenated data to obtain the affinity matrix. However, the affinity matrix is not clean and precise. Therefore, we use the SSR method again on the obtained affinity matrix to obtain a more accurate and clean affinity matrix. Furthermore, the two-step SSR is integrated into a unified optimization framework, a clean and accurate affinity matrix can be obtained, and the sum of each column vector of the affinity matrix is constrained to be nonnegative and equal to s (0 < s < 1), which can be adjusted to obtain the best clustering performance. Finally, an efficient optimization algorithm based on the augmented Lagrangian method (ALM) for solving the objective function is also designed. The experimental results on some datasets show that this algorithm has better clustering performance than some state-of-the-art algorithms. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：The COVID-19 pandemic is an ongoing pandemic and is placing additional burden on healthcare systems around the world. Timely and effectively detecting the virus can help to reduce the spread of the disease. Although, RT-PCR is still a gold standard for COVID-19 testing, deep learning models to identify the virus from medical images can also be helpful in certain circumstances. In particular, in situations when patients undergo routine X-rays and/or CT-scans tests but within a few days of such tests they develop respiratory complications. Deep learning models can also be used for pre-screening prior to RT-PCR testing. However, the transparency/interpretability of the reasoning process of predictions made by such deep learning models is essential. In this paper, we propose an interpretable deep learning model that uses positive reasoning process to make predictions. We trained and tested our model over the dataset of chest CT-scan images of COVID-19 patients, normal people and pneumonia patients. Our model gives the accuracy, precision, recall and F-score equal to 99.48%, 0.99, 0.99 and 0.99, respectively. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：A fundamental characteristic of human visual perception is the ability to group together disparate elements in a scene and treat them as a single unit. The mechanisms by which humans create such groupings remain unknown, but grouping seems to play an important role in a wide variety of visual phenomena, and a good understanding of these mechanisms might provide guidance for how to improve machine vision algorithms. Here, we build on a proposal that some groupings are the result of connections in cortical area V2 that join disparate elements, thereby allowing them to be selected and segmented together. In previous instantiations of this proposal, connection formation was based on the anatomy (e.g., extent) of receptive fields, which made connection formation obligatory when the stimulus conditions stimulate the corresponding receptive fields. We now propose dynamic circuits that provide greater flexibility in the formation of connections and that allow for top-down control of perceptual grouping. With computer simulations we explain how the circuits work and show how they can account for a wide variety of Gestalt principles of perceptual grouping, texture segmentation tasks, amodal illusory contours, and ratings of perceived groupings. We propose that human observers use such top-down control to implement task-dependent connection strategies that encourage particular groupings of stimulus elements in order to promote performance on various visual tasks.(C) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Sparse optimization involving the L-0-norm function as the regularization in objective function has a wide application in many fields. In this paper, we propose a projected neural network modeled by a differential equation to solve a class of these optimization problems, in which the objective function is the sum of a nonsmooth convex loss function and the regularization defined by the L-0-norm function. This optimization problem is not only nonconvex, but also discontinuous. To simplify the structure of the proposed network and let it own better convergence properties, we use the smoothing method, where the new constructed smoothing function for the regularization term plays a key role. We prove that the solution to the proposed network is globally existent and unique, and any accumulation point of it is a critical point of the continuous relaxation model. Except for a special case, which can be easily justified, any critical point is a local minimizer of the considered sparse optimization problem. It is an interesting thing that all critical points own a promising lower bound property, which is satisfied by all global minimizers of the considered problem, but is not by all local minimizers. Finally, we use some numerical experiments to illustrate the efficiency and good performance of the proposed method for solving this class of sparse optimization problems, which include the most widely used models in feature selection of classification learning. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Most existing automatic kinship verification methods focus on learning the optimal distance metrics between family members. However, learning facial features and kinship features simultaneously may cause the proposed models to be too weak. In this work, we explore the possibility of bridging this gap by developing knowledge-based tensor models based on pre-trained multi-view models. We propose an effective knowledge-based tensor similarity extraction framework for automatic facial kinship verification using four pre-trained networks (i.e., VGG-Face, VGG-F, VGG-M, and VGG-S). Therefore, knowledge-based deep face and general features (such as identity, age, gender, ethnicity, expression, lighting, pose, contour, edges, corners, shape, etc.) were successfully fused by our tensor design to understand the kinship cue. Multiple effective representations are learned for kinship verification statements (children and parents) using a margin maximization learning scheme based on Tensor Cross-view Quadratic Exponential Discriminant Analysis. Through the exponential learning process, the large gap between distributions of the same family can be reduced to the maximum, while the small gap between distributions of different families is simultaneously increased. The WCCN metric successfully reduces the intra-class variability problem caused by deep features. The explanation of black-box models and the problems of ubiquitous face recognition are considered in our system. The extensive experiments on four challenging datasets show that our system performs very well compared to state-of-the-art approaches. (c) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Adversarial domain adaptation has made remarkable in promoting feature transferability, while recent work reveals that there exists an unexpected degradation of feature discrimination during the procedure of learning transferable features. This paper proposes an informative pairs mining based adaptive metric learning (IPM-AML), where a novel two-triplet-sampling strategy is advanced to select informative positive pairs from the same classes and informative negative pairs from different classes, and a metric loss imposed with special weights is further utilized to adaptively pay more attention to those more informative pairs which can adaptively improve discrimination. Then, we incorporate IPM-AML into popular conditional domain adversarial network (CDAN) to learn feature representation that is transferable and discriminative desirably (IPM-AML-CDAN). To ensure the reliability of pseudo target labels in the whole training process, we select more confident target ones whose predicted scores are higher than a given threshold T, and also provide theoretical validation for this simple threshold strategy. Extensive experiment results on four cross-domain benchmarks validate that IPM-AML-CDAN can achieve competitive results compared with state-of-the-art approaches. (C)& nbsp;2022 Elsevier Ltd. All rights reserved.
Gharsallaoui, Mohammed AmineAkdag, Hatice CamgozRekik, IslemChaari, Nada...
14页
查看更多>>摘要：Multigraphs with heterogeneous views present one of the most challenging obstacles to classification tasks due to their complexity. Several works based on feature selection have been recently proposed to disentangle the problem of multigraph heterogeneity. However, such techniques have major drawbacks. First, the bulk of such works lies in the vectorization and the flattening operations, failing to preserve and exploit the rich topological properties of the multigraph. Second, they learn the classification process in a dichotomized manner where the cascaded learning steps are pieced in together independently. Hence, such architectures are inherently agnostic to the cumulative estimation error from step to step. To overcome these drawbacks, we introduce MICNet (multigraph integration and classifier network), the first end-to-end graph neural network based model for multigraph classification. First, we learn a single-view graph representation of a heterogeneous multigraph using a GNN based integration model. The integration process in our model helps tease apart the heterogeneity across the different views of the multigraph by generating a subject-specific graph template while preserving its geometrical and topological properties conserving the node-wise information while reducing the size of the graph (i.e., number of views). Second, we classify each integrated template using a geometric deep learning block which enables us to grasp the salient graph features. We train, in end-to-end fashion, these two blocks using a single objective function to optimize the classification performance. We evaluate our MICNet in gender classification using brain multigraphs derived from different cortical measures. We demonstrate that our MICNet significantly outperformed its variants thereby showing its great potential in multigraph classification.
NSTL
Elsevier