A deep convolutional neural network (CNN) has been widely used in image classification and gives better classification accuracy than the other techniques. The softmax cross-entropy loss function is often used for classification tasks. There are some works to introduce the additional terms in the objective function for training to make the features of the output layer more discriminative. The neuron-wise discriminant criterion makes the input feature of each neuron in the output layer discriminative by introducing the discriminant criterion to each of the features. Similarly, the center loss was introduced to the features before the softmax activation function for face recognition to make the deep features discriminative. The ReLU function is often used for the network as an active function in the hidden layers of the CNN. However, it is observed that the deep features trained by using the ReLU function are not discriminative enough and show elongated shapes. In this paper, we propose to use the neuron-wise discriminant criterion at the output layer and the center-loss at the hidden layer. Also, we introduce the online computation of the means of each class with the exponential forgetting. We named them adaptive neuron-wise discriminant criterion and adaptive center loss, respectively. The effectiveness of the integration of the adaptive neuron-wise discriminant criterion and the adaptive center loss is shown by the experiments with MNSIT, FashionMNIST, CIFAR10, CIFAR100, and STL10. Source code is at https://github.com/i13abe/Adaptive-discriminant-and-center
City University of Hong Kong（香港城市大学）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
Deep supervised hashing has emerged as an influential solution to large-scale semantic image retrieval problems in computer vision. In the light of recent progress, convolutional neural network based hashing methods typically seek pair-wise or triplet labels to conduct the similarity preserving learning. However, complex semantic concepts of visual contents are hard to capture by similar/dissimilar labels, which limits the retrieval performance. Generally, pair-wise or triplet losses not only suffer from expensive training costs but also lack in extracting sufficient semantic information. In t…
Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences, Institute of Computing Technology, CAS（中国科学院计算技术研究所智能信息处理重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；Peng Cheng Laboratory（鹏城实验室）；Tomorrow Advancing Life Education Group（好未来教育集团）
Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as a useful approach. However, these artificial occlusions are commonly generated by adding a black rectangle or several object templates including sunglasses, scarfs and phones, which cannot well simulate the realistic occlusions. In this paper, based on the argument that the occlusion essentially damages a group of neurons, we propose a novel and elegant occl…
Visual Detector Compression via Location-Aware Discriminant Analysis
Dept. of Computer Science, University of Alabama at Birmingham（阿拉巴马大学伯明翰分校计算机科学系）；Dept. of Computer Science, Bowling Green State University（伯灵顿州立大学计算机科学系）
University of Notre Dame（圣母大学）；Harvard University（哈佛大学）
In this paper, we consider the problem of automatically segmenting neuronal cells in dual-color confocal microscopy images. This problem is a key task in various quantitative analysis applications in neuroscience, such as tracing cell genesis in Danio rerio (zebrafish) brains. Deep learning, especially using fully convolutional networks (FCN), has profoundly changed segmentation research in biomedical imaging. We face two major challenges in this problem. First, neuronal cells may form dense clusters, making it difficult to correctly identify all individual cells (even to human experts). Conse…
Most of today's popular deep architectures are hand-engineered to be generalists. However, this design procedure usually leads to massive redundant, useless, or even harmful features for specific tasks. Unnecessarily high complexities render deep nets impractical for many real-world applications, especially those without powerful GPU support. In this paper, we attempt to derive task-dependent compact models from a deep discriminant analysis perspective. We propose an iterative and proactive approach for classification tasks which alternates between (1) a pushing step, with an objective to simu…
South China University of Technology（华南理工大学）；The University of Sydney（悉尼大学）
Many machine learning problems concern with discovering or associating common patterns in data of multiple views or modalities. Multi-view learning is of the methods to achieve such goals. Recent methods propose deep multi-view networks via adaptation of generic Deep Neural Networks (DNNs), which concatenate features of individual views at intermediate network layers (i.e., fusion layers). In this work, we study the problem of multi-view learning in such end-to-end networks. We take a regularization approach via multi-view learning criteria, and propose a novel, effective, and efficient neuron…
Recurrent neural networks (RNNs) are capable of modeling the temporal dynamics of complex sequential information. However, the structures of existing RNN neurons mainly focus on controlling the contributions of current and historical information but do not explore the different importance levels of different elements in an input vector of a time slot. We propose adding a simple yet effective Element-wiseAttention Gate (EleAttG) to an RNN block (e.g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability. For an RNN block, an EleAttG is added to …
Sydney Nano Institute, University of Sydney（悉尼大学悉尼纳米研究所）；School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；Paige AI；Sydney Pharmacy School, University of Sydney（悉尼大学药学院）
Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background. Due to the variety of neuron morphology and the lack of large neuron datasets, most of current neuron segmentation models rely on introducing complex and s…
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device. Yet the complexity of these neural networks needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies focus on squeezing the redundancy within a single neural network. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. …
Xian Jiaotong University（西安交通大学）；Microsoft Research Asia（微软亚洲研究院）；Alibaba Group（阿里巴巴集团）
Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on controlling the contributions of current and previous information. However, the exploration of different importance levels of different elements within an input vector is always ignored. We propose a simple yet effective Element-wise-Attention Gate (EleAttG), which can be easily added to an RNN block (e.g. all RNN neurons in an RNN layer), to empower the RNN neurons to have attentiveness capability. For an RNN block, …
University of Electronic Science and Technology of China（电子科技大学）
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices. Among many pruning granularities, neuron level pruning will remove redundant neurons and filters in the model and result in thinner networks. In this paper, we propose a gradually global pruning scheme for neuron level pruning. In each pruning step, a small percent of neurons were selected and dropped across all layers in the model. We also propose a simple method to eliminate the biases in evaluating the importance of neurons to make th…
We propose doubly nested network(DNNet) where all neurons represent their own sub-models that solve the same task. Every sub-model is nested both layer-wise and channel-wise. While nesting sub-models layer-wise is straight-forward with deep-supervision as proposed in \cite{xie2015holistically}, channel-wise nesting has not been explored in the literature to our best knowledge. Channel-wise nesting is non-trivial as neurons between consecutive layers are all connected to each other. In this work, we introduce a technique to solve this problem by sorting channels topologically and connecting neu…
Massachusetts Institute of Technology（麻省理工学院）；Amazon（亚马逊）；National Taiwan University（台湾大学）
While deep neural networks have succeeded in several visual applications, such as object recognition, detection, and localization, by reaching very high classification accuracies, it is important to note that many real-world applications demand varying costs for different types of misclassification errors, thus requiring cost-sensitive classification algorithms. Current models of deep neural networks for cost-sensitive classification are restricted to some specific network structures and limited depth. In this paper, we propose a novel framework that can be applied to deep neural networks with…
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a deep neural network are initialized with: random values, greedy layer-wise pre-training (usually as Deep Belief Network or as auto-encoder) or by re-using the layers from another network (transfer learning). Hence, many training epochs are needed before meaningful weights are learned, or a rather similar dataset is required for seeding a fine-tuning of transfer learning. In this paper, we describe how to turn an LDA in…
Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender classification. Although deep CNN nets have been very effective for a multitude of classification tasks, their high space and time demands make them impractical for personal computers and mobile devices without a powerful GPU. In this paper, we develop a 16-layer, yet lightweight, neural network which boosts efficiency while maintaining high accuracy. Our net is pruned from the VGG-16 model starting from the last convolutional (conv) layer where we find neuron activations are highly uncorrelated …
Lahore University of Management Sciences（拉合尔管理科学大学）
One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters based on their importance or depth-wise by removing layers and blocks. Width wise pruning (filter pruning) is commonly performed via learnable gates or switches and sparsity regularizers whereas pruning of layers has so far been performed arbitrarily by manually designing a smaller network usually referred to as a student network. We propose a comprehensive pruning stra…
University of Pittsburgh（匹兹堡大学）；SUNY at Buffalo（纽约州立大学布法罗分校）；Duke University（杜克大学）；Midea Corporate Research Center（美的集团研究院）
Deep Convolutional Neural Networks~(CNNs) offer remarkable performance of classifications and regressions in many high-dimensional problems and have been widely utilized in real-word cognitive applications. However, high computational cost of CNNs greatly hinder their deployment in resource-constrained applications, real-time systems and edge computing platforms. To overcome this challenge, we propose a novel filter-pruning framework, two-phase filter pruning based on conditional entropy, namely \textit{2PFPCE}, to compress the CNN models and reduce the inference time with marginal performance…
With deep learning's success, a limited number of popular deep nets have been widely adopted for various vision tasks. However, this usually results in unnecessarily high complexities and possibly many features of low task utility. In this paper, we address this problem by introducing a task-dependent deep pruning framework based on Fisher's Linear Discriminant Analysis (LDA). The approach can be applied to convolutional, fully-connected, and module-based deep network structures, in all cases leveraging the high decorrelation of neuron motifs found in the pre-decision space and cross-layer dec…
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged as one of the key ingredients to reduce the size of neural networks for their deployments to resource-limited devices. In order to overcome the nature of transforming continuous activations and weights to discrete ones, recent study called Relaxed Quantization (RQ) [Louizos et al. 2019] successfully employ the popular Gumbel-Softmax that allows this transformation with efficient gradient-based optimization. However, RQ with this Gumbel-Softmax relaxation still suffers from bias-varian…
An Adaptive Method Stabilizing Activations for Enhanced Generalization
Department of Statistics University of Georgia（佐治亚大学统计学系）；School of Computing University of Georgia（佐治亚大学计算机学院）；School of Electrical Engineering Hanyang University（翰林大学电气工程学院）
Purpose: We present image classifiers based on Dense Convolutional Networks and transfer learning to classify chest X-ray images according to three labels: COVID-19, pneumonia and normal. Methods: We fine-tuned neural networks pretrained on ImageNet and applied a twice transfer learning approach, using NIH ChestX-ray14 dataset as an intermediate step. We also suggested a novelty called output neuron keeping, which changes the twice transfer learning technique. In order to clarify the modus operandi of the models, we used Layer-wise Relevance Propagation (LRP) to generate heatmaps. Results: We …
VinAI Research（VinAI研究院）；Hanoi University of Science and Technology（河内科技大学）；University of Texas, Austin（德克萨斯大学奥斯汀分校）；Monash University（莫纳什大学）
Layer-wise model fusion via optimal transport, named OTFusion, applies soft neuron association for unifying different pre-trained networks to save computational resources. While enjoying its success, OTFusion requires the input networks to have the same number of layers. To address this issue, we propose a novel model fusion framework, named CLAFusion, to fuse neural networks with a different number of layers, which we refer to as heterogeneous neural networks, via cross-layer alignment. The cross-layer alignment problem, which is an unbalanced assignment problem, can be solved efficiently usi…
Purdue University（普渡大学）；Michigan State University（密歇根州立大学）；Texas Tech University（德克萨斯理工大学）
We propose reproducing activation functions (RAFs) to improve deep learning accuracy for various applications ranging from computer vision to scientific computing. The idea is to employ several basic functions and their learnable linear combination to construct neuron-wise data-driven activation functions for each neuron. Armed with RAFs, neural networks (NNs) can reproduce traditional approximation tools and, therefore, approximate target functions with a smaller number of parameters than traditional NNs. In NN training, RAFs can generate neural tangent kernels (NTKs) with a better condition …
Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-generation of neural networks due to their event-driven and low-powered nature. SNNs, however, are difficult to train, mainly owing to their complex dynamics of neurons and non-differentiable spike operations. Furthermore, their applications have been limited to relatively simple …
Convolution is a central operation in Convolutional Neural Networks (CNNs), which applies a kernel to overlapping regions shifted across the image. However, because of the strong correlations in real-world image data, convolutional kernels are in effect re-learning redundant data. In this work, we show that this redundancy has made neural network training challenging, and propose network deconvolution, a procedure which optimally removes pixel-wise and channel-wise correlations before the data is fed into each layer. Network deconvolution can be efficiently calculated at a fraction of the comp…
Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY)（南洋理工大学-不列颠哥伦比亚大学活跃老年生活卓越联合研究中心（LILY））；Nanyang Technological University（南洋理工大学）；Alibaba-NTU Singapore Joint Research Institute（阿里巴巴-南洋理工大学新加坡联合研究院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Electroencephalography (EEG) measures the neuronal activities in different brain regions via electrodes. Many existing studies on EEG-based emotion recognition do not fully exploit the topology of EEG channels. In this paper, we propose a regularized graph neural network (RGNN) for EEG-based emotion recognition. RGNN considers the biological topology among different brain regions to capture both local and global relations among different EEG channels. Specifically, we model the inter-channel relations in EEG signals via an adjacency matrix in a graph neural network where the connection and spa…
