检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Guo, Qingbei Wu, Xiao-Jun Kittler, Josef Feng, Zhiquan Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China Shandong Provincial Key Laboratory of Network based Intelligent Computing University of Jinan Jinan250022 China Centre for Vision Speech and Signal Processing University of Surrey GuildfordGU2 7XH United Kingdom

Automated neural network design has received ever-increasing attention with the evolution of deep convolutional neural networks (CNNs), especially involving their deployment on embedded and mobile platforms. One of the biggest problems that neural architecture search (NAS) confronts is that a large number of candidate neural architectures are required to train, using, for instance, reinforcement learning and evolutionary optimisation algorithms, at a vast computation cost. Even recent differentiable neural architecture search (DNAS) samples a small number of candidate neural architectures based on the probability distribution of learned architecture parameters to select the final neural architecture. To address this computational complexity issue, we introduce a novel architecture parameterisation based on scaled sigmoid function, and propose a general Differentiable Neural Architecture Learning (DNAL) method to optimize the neural architecture without the need to evaluate candidate neural networks. Specifically, for stochastic supernets as well as conventional CNNs, we build a new channel-wise module layer with the architecture components controlled by a scaled sigmoid function. We train these neural network models from scratch. The network optimization is decoupled into the weight optimization and the architecture optimization, which avoids the interaction between the two types of parameters and alleviates the vanishing gradient problem. We address the non-convex optimization problem of neural architecture by the continuous scaled sigmoid method with convergence guarantees. Extensive experiments demonstrate our DNAL method delivers superior performance in terms of neural architecture search cost, and adapts to conventional CNNs (e.g., VGG16 and ResNet50), lightweight CNNs (e.g., MobileNetV2) and stochastic supernets (e.g., ProxylessNAS). The optimal networks learned by DNAL surpass those produced by the state-of-the-art methods on the benchmark CIFAR-10 and ImageN

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

UMFA: A photorealistic style transfer method based on U-Net and multi-layer feature aggregation

arXiv

引用

arXiv 2021年

作者： Rao, Dongyu Wu, Xiao-Jun Li, Hui Kittler, Josef Xu, Tianyang Jiangnan University Jiangsu Provincial Engineerinig Laboratory of Pattern Recognition and Computational Intelligence School of Artificial Intelligence and Computer Science Lihu Avenue Wuxi214122 China University of Surrey Centre for Vision Speech and Signal Processing GuildfordGU2 7XH United Kingdom

In this paper, we propose a photorealistic style transfer network to emphasize the natural effect of photo realistic image stylization. In general, distortion of the image content and lacking of details are two typical issues in the style transfer field. To this end, we design a novel framework employing the U-Net structure to maintain the rich spatial clues, with a multi-layer feature aggregation (MFA) method to simultaneously provide the details obtained by the shallow layers in the stylization processing. In particular, an encoder based on the dense block and a decoder form a symmetrical structure of U-Net are jointly staked to realize an effective feature extraction and image reconstruc tion. Besides, a transfer module based on MFA and "adaptive instance normalization" (AdaIN) is inserted in the skip connection positions to achieve the stylization. Accordingly, the stylized image possesses the texture of a real photo and preserves rich content details without introducing any mask or post-processing steps. The experimental results on public datasets demonstrate that our method achieves a more faithful structural similarity with a lower style loss, reflecting the effectiveness and merit of our approach. © 2021, CC0.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multiplication fusion of sparse and collaborative-competitive representation for image classification

arXiv

引用

arXiv 2020年

作者： Li, Zi-Qi Sun, Jun Wu, Xiao-Jun Yin, He-Feng School of Internet of Things Engineering Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

Representation based classification methods have become a hot research topic during the past few years, and the two most prominent approaches are sparse representation based classification (SRC) and collaborative representation based classification (CRC). CRC reveals that it is the collaborative representation rather than the sparsity that makes SRC successful. Nevertheless, the dense representation of CRC may not be discriminative which will degrade its performance for classification tasks. To alleviate this problem to some extent, we propose a new method called sparse and collaborative-competitive representation based classification (SCCRC) for image classification. Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively. Then the fused coefficient is derived by multiplying the coefficients of SRC and CCRC. Finally, the test sample is designated to the class that has the minimum residual. Experimental results on several benchmark databases demonstrate the efficacy of our proposed SCCRC. The source code of SCCRC is accessible at https://***/li-zi-qi/SCCRC. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Learning efficient structured dictionary for image classification

arXiv

引用

arXiv 2020年

作者： Li, Zi-Qi Sun, Jun Wu, Xiao-Jun Yin, He-Feng Jiangnan University School of Internet of Things Engineering Lihu Avenue Wuxi China Jiangsu Provincial Laboratory of Pattern Recognition and Computational Intelligence Lihu Avenue Wuxi China

Recent years have witnessed the success of dictionary learning (DL) based approaches in the domain of pattern classification. In this paper, we present an efficient structured dictionary learning (ESDL) method which takes both the diversity and label information of training samples into account. Specifically, ESDL introduces alternative training samples into the process of dictionary learning. To increase the discriminative capability of representation coefficients for classification, an ideal regularization term is incorporated into the objective function of ESDL. Moreover, in contrast with conventional DL approaches which impose computationally expensive `1-norm constraint on the coefficient matrix, ESDL employs `2-norm regularization term. Experimental results on benchmark databases (including four face databases and one scene dataset) demonstrate that ESDL outperforms previous DL approaches. More importantly, ESDL can be applied in a wide range of pattern classification tasks. The demo code of our proposed ESDL will be available at https://***/li-zi-qi/ESDL. Copyright © 2020, The Authors. All rights reserved.

关键词： Sampling

来源：评论

学校读者我要写书评

暂无评论

Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning

arXiv

引用

arXiv 2022年

作者： Li, Yun Liu, Zhe Chang, Xiaojun McAuley, Julian Yao, Lina The School of Computer Science and Engineering University of New South Wales SydneyNSW2052 Australia The Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China The School of Computer Science and Engineering University of New South Wales SydneyNSW2052 Australia The Faculty of Engineering and Information Technology University of Technology Sydney SydneyNSW2007 Australia The School of Computer Science and Engineering University of California San Diego San DiegoCA United States CSIRO’s Data61 University of New South Wales SydneyNSW2052 Australia

Zero-Shot Learning (ZSL) aims to transfer classification capability from seen to unseen classes. Recent methods have proved that generalization and specialization are two essential abilities to achieve good performance in ZSL. However, focusing on only one of the abilities may result in models that are either too general with degraded classification ability or too specialized to generalize to unseen classes. In this paper, we propose an end-to-end network, termed as BGSNet, which equips and balances generalization and specialization abilities at the instance and dataset level. Specifically, BGSNet consists of two branches: the Generalization Network (GNet), which applies episodic meta-learning to learn generalized knowledge, and the Balanced Specialization Network (BSNet), which adopts multiple attentive extractors to extract discriminative features and achieve instance-level balance. A novel self-adjusted diversity loss is designed to optimize BSNet with redundancy reduced and diversity boosted. We further propose a differentiable dataset-level balance and update the weights in a linear annealing schedule to simulate network pruning and thus obtain the optimal structure for BSNet with dataset-level balance achieved. Experiments on four benchmark datasets demonstrate our model’s effectiveness. Sufficient component ablations prove the necessity of integrating and balancing generalization and specialization abilities. Copyright © 2022, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Component SPD matrices： A low-dimensional discriminative data descriptor for image set classification

引用

computational Visual Media 2018年第3期4卷 245-252页

作者： Kai-Xuan Chen Xiao-Jun Wu School of loT Engineering 3iangnan University Wuxi 214122 China. Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi 214122 China.

In pattern recognition,the task of image set classification has often been performed by representing data using symmetric positive definite(SPD)matrices,in conjunction with the metric of the resulting Riemannian *** this paper,we propose a new data representation framework for image sets which we call component symmetric positive definite representation(CSPD).Firstly,we obtain sub-image sets by dividing the images in the set into square blocks of the same size,and use a traditional SPD model to describe ***,we use the Riemannian kernel to determine similarities of corresponding subimage ***,the CSPD matrix appears in the form of the kernel matrix for all the sub-image sets;its i,j-th entry measures the similarity between the i-th and j-th sub-image *** Riemannian kernel is shown to satisfy Mercer’s theorem,so the CSPD matrix is symmetric and positive definite,and also lies on a Riemannian *** on three benchmark datasets shows that CSPD is both lower-dimensional and more discriminative data descriptor than standard SPD for the task of image set classification.

关键词： symmetric positive definite （SPD） matricesRiemannian kernel image classificationRiemannian manifold

来源：评论

学校读者我要写书评

暂无评论

Self-grouping convolutional neural networks

arXiv

引用

arXiv 2020年

Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence, which prevents a full exploitation of their potential. To tackle this issue, we propose a novel method of designing self-grouping convolutional neural networks, called SG-CNN, in which the filters of each convolutional layer group themselves based on the similarity of their importance vectors. Concretely, for each filter, we first evaluate the importance value of their input channels to identify the importance vectors, and then group these vectors by clustering. Using the resulting data-dependent centroids, we prune the less important connections, which implicitly minimizes the accuracy loss of the pruning, thus yielding a set of diverse group convolution filters. Subsequently, we develop two fine-tuning schemes, i.e. (1) both local and global fine-tuning and (2) global only fine-tuning, which experimentally deliver comparable results, to recover the recognition capacity of the pruned network. Comprehensive experiments carried out on the CIFAR-10/100 and ImageNet datasets demonstrate that our self-grouping convolution method adapts to various state-of-the-art CNN architectures, (Figure presented) Figure 1: Evolution of group convolutions. (a) Regular convolution. (b) Regular group convolution. (c) Permuting group convolution. (d) Learned group convolution. (d) Self-grouping convolution. Note that white channels represent the ignored input channels, and gray channels indicate the reused input channels. such as ResNet and DenseNet, and delivers superior performance in terms of compression ratio, speedup and recognition accuracy. We demonstrate the ability of SG-CNN

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Spatial Residual Layer and Dense Connection Block Enhanced Spatial Temporal Graph Convolutional Network for Skeleton-Based Action recognition

Spatial Residual Layer and Dense Connection Block Enhanced S...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Cong Wu Xiao-Jun Wu Josef Kittler School of IOT Engineering Jiangnan University China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence CVSSP University of Surrey UK

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Recent research has shown that modeling the dynamic joint features of the human body by a graph convolutional network (GCN) is a groundbreaking approach for skeleton-based action recognition, especially for the recognition of the body-motion, human-object and human-human interactions. Nevertheless, how to model and utilize coherent skeleton information comprehensively is still an open problem. In order to capture the rich spatiotemporal information and utilize features more effectively, we introduce a spatial residual layer and a dense connection block enhanced spatial temporal graph convolutional network. More specifically, our work introduces three aspects. Firstly, we extend spatial graph convolution to spatial temporal graph convolution of cross-domain residual to extract more precise and informative spatiotemporal feature, and reduce the training complexity by feature fusion in the, so-called, spatial residual layer. Secondly, instead of simply superimposing multiple similar layers, we use dense connection to take full advantage of the global information. Thirdly, we combine the above mentioned two components to create a spatial temporal graph convolutional network (ST-GCN), referred to as SDGCN. The proposed graph representation has a new structure. We perform extensive experiments on two large datasets: Kinetics and NTU-RGB+D. Our method achieves a great improvement in performance compared to the mainstream methods. We evaluate our method quantitatively and qualitatively, thus proving its effectiveness.

关键词： Convolution Spatiotemporal phenomena Joints Feature extraction Two dimensional displays Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Adaptive multi-modal fusion hashing via hadamard matrix

arXiv

引用

arXiv 2020年

作者： Yu, Jun Zhang, Donglin Shu, Zhenqiu Chen, Feng The College of Computer and Communication Engineering Zhengzhou University of Light Industry Zhengzhou China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China The Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China The School of Computer Science and Technology Anhui University of Technology Ma'anshan China

Hashing plays an important role in information retrieval, due to its low storage and high speed of processing. Among the techniques available in the literature, multi-modal hashing, which can encode heterogeneous multi-modal features into compact hash codes, has received particular attention. Most of the existing multi-modal hashing methods adopt the fixed weighting factors to fuse multiple modalities for any query data, which cannot capture the variation of different queries. Besides, many methods introduce hyper-parameters to balance many regularization terms that make the optimization harder. Meanwhile, it is time-consuming and labor-intensive to set proper parameter values. The limitations may significantly hinder their promotion in real applications. In this paper, we propose a simple, yet effective method that is inspired by the Hadamard matrix. The proposed method captures the multi-modal feature information in an adaptive manner and preserves the discriminative semantic information in the hash codes. Our framework is flexible and involves a very few hyper-parameters. Extensive experimental results show the method is effective and achieves superior performance compared to state-of-the-art algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Cross-modal subspace learning via Kernel correlation maximization and discriminative structure preserving

arXiv

引用

arXiv 2019年

作者： Yu, Jun Wu, Xiao-Jun School of IoT Engineering Jiangnan University Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition Computational Intelligence Jiangnan University Wuxi214122 China

The measure between heterogeneous data is still an open problem. Many research works have been developed to learn a common subspace where the similarity between different modalities can be calculated directly. However, most of existing works focus on learning a latent subspace but the semantically structural information is not well preserved. Thus, these approaches cannot get desired results. In this paper, we propose a novel framework, termed Cross-modal subspace learning via Kernel correlation maximization and Discriminative structure-preserving (CKD), to solve this problem in two aspects. Firstly, we construct a shared semantic graph to make each modality data preserve the neighbor relationship semantically. Secondly, we introduce the Hilbert-Schmidt Independence Criteria (HSIC) to ensure the consistency between feature-similarity and semantic-similarity of samples. Our model not only considers the inter-modality correlation by maximizing the kernel correlation but also preserves the semantically structural information within each modality. The extensive experiments are performed to evaluate the proposed framework on the three public datasets. The experimental results demonstrated that the proposed CKD is competitive compared with the classic subspace learning methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：