检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2021年第1期2卷 58-70页

作者： Li, Ziqiang Tao, Rentuo Wang, Jie Li, Fu Niu, Hongjing Yue, Mingdao Li, Bin The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems University of Science and Technology of China Hefei230052 China The Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230052 China The School of Information Science and Technology University of Science and Technology of China Hefei230052 China The College of Mechanical and Electrical Engineering Suzhou University Suzhou234000 China

With the success of generative adversarial networks (GANs) on various real-world applications, the controllability and security of GANs have raised more and more concerns from the community. Specifically, understanding the latent space of GANs, i.e., obtaining the completely decoupled latent space, is essential for applications in some secure scenarios. At present, there is no quantitative method to measure the decoupling of latent space, which is not conducive to the development of the community. In this article, we propose two methods to measure the sensitivity of latent dimensions: one is a sequential intervention method, and the other is an optimization-based method that measures the sensitivity in both the value and the direction. With these two methods, the decoupling of latent space can be measured by the sparsity of the sensitivity vector obtained. The effectiveness of the proposed methods has been verified by experiments on the representative GANs. Code will be available at https://***/iceli1007/latent-analysis-of. Impact Statement-Generative adversarial networks (GANs) is a popular technology in image generation. Benefiting from the development of neural networks, GANs have been widely used in many real-world tasks, such as super-resolution, image translation, and image inpainting. However, the understanding of the generator in GANs as a map from latent space (represented in a multidimensional vector) to image space is incomplete. To make better use of GANs, more insight into the generation process is required. The motivation of this article is to develop methods to analyze the influence of each dimension of latent space on the generated results, and to measure the decoupling of latent space, the knowledge obtained will be useful for the development of more precise controllable image generation technology. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

DA-RefineNet: Dual-inputs Attention RefineNet for Whole Slide Image Segmentation

DA-RefineNet: Dual-inputs Attention RefineNet for Whole Slid...

引用

International Conference on Pattern Recognition

作者： Ziqiang Li Rentuo Tao Qianrun Wu Bin Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Hefei Anhui China School of foreign studies Hefei University of Technology Hefei Anhui China

Automatic medical image segmentation has wide applications for disease diagnosing. However, it is much more challenging than natural optical image segmentation due to the high-resolution of medical images and the corresponding huge computation cost. The sliding window is a commonly used technique for whole slide image (WSI) segmentation, however, for these methods based on the sliding window, the main drawback is lacking global contextual information for supervision. In this paper, we propose a dual-inputs attention network (denoted as DA-RefineNet) for WSI segmentation, where both local fine-grained information and global coarse information can be efficiently utilized. Sufficient comparative experiments are conducted to evaluate the effectiveness of the proposed method, the results prove that the proposed method can achieve better performance on WSI segmentation compared to methods relying on single-input.

关键词： Knowledge engineering Image segmentation Semantics Breast Feature extraction Optical imaging Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation

Interpreting the Latent Space of GANs via Correlation Analys...

引用

International Conference on Pattern Recognition

作者： Ziqiang Li Rentuo Tao Hongjing Niu Mingdao Yue Bin Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Hefei Anhui China College of Mechanical and Electrical Engineering Suzhou University Suzhou Anhui China

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution, and drug discovery, etc. By now, the inner process of GANs is far from being understood. To get a deeper insight into the intrinsic mechanism of GANs, in this paper, a method for interpreting the latent space of GANs by analyzing the correlation between latent variables and the corresponding semantic contents in generated images is proposed. Unlike previous methods that focus on dissecting models via feature visualization, the emphasis of this work is put on the variables in latent space, i.e. how the latent variables affect the quantitative analysis of generated results. Given a pre-trained GAN model with weights fixed, the latent variables are intervened to analyze their effect on the semantic content in generated images. A set of controlling latent variables can be derived for specific content generation, and the controllable semantic content manipulation is achieved. The proposed method is testified on the datasets Fashion-MNIST and UT Zappos50K, experiment results show its effectiveness.

关键词： Drugs Visualization Analytical models Correlation Statistical analysis Image synthesis Semantics

来源：评论

学校读者我要写书评

暂无评论

Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation

arXiv

引用

arXiv 2020年

作者： Li, Ziqiang Tao, Rentuo Niu, Hongjing Li, Bin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Anhui China

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution and drug discovery, etc., by now, the inner process of GANs is far from been understood. To get deeper insight of the intrinsic mechanism of GANs, in this paper, a method for interpreting the latent space of GANs by analyzing the correlation between latent variables and the corresponding semantic contents in generated images is proposed. Unlike previous methods that focus on dissecting models via feature visualization, the emphasis of this work is put on the variables in latent space, i.e. how the latent variables affect the quantitative analysis of generated results. Given a pretrained GAN model with weights fixed, the latent variables are intervened to analyze their effect on the semantic content in generated images. A set of controlling latent variables can be derived for specific content generation, and the controllable semantic content manipulation be achieved. The proposed method is testified on the datasets Fashion-MNIST and UT Zappos50K, experiment results show its effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improving resistance to adversarial deformations by regularizing gradients

arXiv

引用

arXiv 2020年

作者： Xia, Pengfei Li, Bin CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Department of Electronic Engineering and Information Science University of Science of Technology of China Hefei China

Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. Currently, most defense methods are designed to defend against additive noise attacks, their performance cannot be guaranteed when against non-additive noise attacks. In this paper, we focus on adversarial deformations, a typical class of non-additive noise attacks, and propose a flow gradient regularization with random start to improve the resistance of models. Theoretically, we prove that, compared with input gradient regularization, regularizing flow gradients is able to get a tighter bound. Across multiple datasets, architectures, and adversarial deformations, our experimental results consistently indicate that models trained with flow gradient regularization can acquire a better resistance than trained with input gradient regularization with a large margin. Moreover, compared with adversarial training, our method can achieve better results in optimization-based and gradient-free attacks, and combining these two methods can improve the resistance against deformation attacks further. Finally, we give a unified form of gradient regularization, which can be used to derive the corresponding form when facing other types of attack. Copyright © 2020, The Authors. All rights reserved.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

Transform-Invariant Convolutional Neural Networks for Image Classification and Search

arXiv

引用

arXiv 2019年

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation & Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Convolutional neural networks (CNNs) have achieved state-of-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transform-invariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. The code is available at https: ACM ISBN 978-1-4503-2138-9. Copyright © 2019, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Technology Roadmap for Flexible Sensors

引用

ACS NANO 2023年第6期17卷 5211-5295页

作者： Luo, Yifei Abidian, Mohammad Reza Ahn, Jong-Hyun Akinwande, Deji Andrews, Anne M. Antonietti, Markus Bao, Zhenan Berggren, Magnus Berkey, Christopher A. Bettinger, Christopher John Chen, Jun Chen, Peng Cheng, Wenlong Cheng, Xu Choi, Seon-Jin Chortos, Alex Dagdeviren, Canan Dauskardt, Reinhold H. Di, Chong-an Dickey, Michael D. Duan, Xiangfeng Facchetti, Antonio Fan, Zhiyong Fang, Yin Feng, Jianyou Feng, Xue Gao, Huajian Gao, Wei Gong, Xiwen Guo, Chuan Fei Guo, Xiaojun Hartel, Martin C. He, Zihan Ho, John S. Hu, Youfan Huang, Qiyao Huang, Yu Huo, Fengwei Hussain, Muhammad M. Javey, Ali Jeong, Unyong Jiang, Chen Jiang, Xingyu Kang, Jiheong Karnaushenko, Daniil Khademhosseini, Ali Kim, Dae-Hyeong Kim, Il-Doo Kireev, Dmitry Kong, Lingxuan Lee, Chengkuo Lee, Nae-Eung Lee, Pooi See Lee, Tae-Woo Li, Fengyu Li, Jinxing Liang, Cuiyuan Lim, Chwee Teck Lin, Yuanjing Lipomi, Darren J. Liu, Jia Liu, Kai Liu, Nan Liu, Ren Liu, Yuxin Liu, Yuxuan Liu, Zhiyuan Liu, Zhuangjian Loh, Xian Jun Lu, Nanshu Lv, Zhisheng Magdassi, Shlomo Malliaras, George G. Matsuhisa, Naoji Nathan, Arokia Niu, Simiao Pan, Jieming Pang, Changhyun Pei, Qibing Peng, Huisheng Qi, Dianpeng Ren, Huaying Rogers, John A. Rowe, Aaron Schmidt, Oliver G. Sekitani, Tsuyoshi Seo, Dae-Gyo Shen, Guozhen Sheng, Xing Shi, Qiongfeng Someya, Takao Song, Yanlin Stavrinidou, Eleni Su, Meng Sun, Xuemei Takei, Kuniharu Tao, Xiao-Ming Tee, Benjamin C. K. Thean, Aaron Voon-Yew Trung, Tran Quang Wan, Changjin Wang, Huiliang Wang, Joseph Wang, Ming Wang, Sihong Wang, Ting Wang, Zhong Lin Weiss, Paul S. Wen, Hanqi Xu, Sheng Xu, Tailin Yan, Hongping Yan, Xuzhou Yang, Hui Yang, Le Yang, Shuaijian Yin, Lan Yu, Cunjiang Yu, Guihua Yu, Jing Yu, Shu-Hong Yu, Xinge Zamburg, Evgeny Zhang, Haixia Zhang, Xiangyu Zhang, Xiaosheng Zhang, Xueji Zhang, Yihui Zhang, Yu Zhao, Siyuan Zhao, Xuanhe Zheng, Yuanjin Zheng, Yu-Qing Zheng, Zijian Zhou, Tao Zhu, Bowen Zhu, Ming Zhu, Rong Zhu, Yangzhi Zhu, Yong Zou, Guijin Chen, Xiaodong 08-03 Innovis Singapore 138634 Republic of Singapore Innovative Centre for Flexible Devices (iFLEX) School of Materials Science and Engineering Nanyang Technological University Singapore 639798 Singapore Department of Biomedical Engineering University of Houston Houston Texas 77024 United States School of Electrical and Electronic Engineering Yonsei University Seoul 03722 Republic of Korea Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 United States Microelectronics Research Center The University of Texas at Austin Austin Texas 78758 United States Department of Chemistry and Biochemistry California NanoSystems Institute and Department of Psychiatry and Biobehavioral Sciences Semel Institute for Neuroscience and Human Behavior and Hatos Center for Neuropharmacology University of California Los Angeles Los Angeles California 90095 United States Colloid Chemistry Department Max Planck Institute of Colloids and Interfaces 14476 Potsdam Germany Department of Chemical Engineering Stanford University Stanford California 94305 United States Laboratory of Organic Electronics Department of Science and Technology Campus Norrköping Linköping University 83 Linköping Sweden Wallenberg Initiative Materials Science for Sustainability (WISE) and Wallenberg Wood Science Center (WWSC) SE-100 44 Stockholm Sweden Department of Materials Science and Engineering Stanford University Stanford California 94301 United States Department of Biomedical Engineering and Department of Materials Science and Engineering Carnegie Mellon University Pittsburgh Pennsylvania 15213 United States Department of Bioengineering University of California Los Angeles Los Angeles California 90095 United States School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singapore 637457 Singapore Nanobionics Group Department of Chemical and Biological Engineering Monash University Clayton Australia 3800 Monash

Humans rely increasingly on sensors to address grand challenges and to improve quality of life in the era of digitalization and big data. For ubiquitous sensing, flexible sensors are developed to overcome the limitations of conventional rigid counterparts. Despite rapid advancement in bench-side research over the last decade, the market adoption of flexible sensors remains limited. To ease and to expedite their deployment, here, we identify bottlenecks hindering the maturation of flexible sensors and propose promising solutions. We first analyze continued...challenges in achieving satisfactory sensing performance for real-world applications and then summarize issues in compatible sensor-biology interfaces, followed by brief discussions on powering and connecting sensor networks. Issues en route to commercialization and for sustainable growth of the sector are also analyzed, highlighting environmental concerns and emphasizing nontechnical issues such as business, regulatory, and ethical considerations. Additionally, we look at future intelligent flexible sensors. In proposing a comprehensive roadmap, we hope to steer research efforts towards common goals and to guide coordinated development strategies from disparate communities. Through such collaborative

关键词： soft materials mechanics engineering flexible electronics conformable sensors bioelectronics human-machine interfaces body area sensor networks technology translation sustainable electronics

来源：评论

学校读者我要写书评

暂无评论

Domain generalization via conditional invariant representations

arXiv

引用

arXiv 2018年

作者： Li, Ya Gong, Mingming Tian, Xinmei Liu, Tongliang Tao, Dacheng CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application Systems University of Science and Technology of China UBTECH Sydney Artificial Intelligence Institute SIT FEIT University of Sydney Department of Philosophy Carnegie Mellon University Department of Biomedical Informatics University of Pittsburgh

Domain generalization aims to apply knowledge gained from multiple labeled source domains to unseen target domains. The main difficulty comes from the dataset bias: Training data and test data have different distributions, and the training set contains heterogeneous samples from different distributions. Let X denote the features, and Y be the class labels. Existing domain generalization methods address the dataset bias problem by learning a domain-invariant representation h(X) that has the same marginal distribution (h(X)) across multiple source domains. The functional relationship encoded in (Y jX) is usually assumed to be stable across domains such that (Y jh(X)) is also invariant. However, it is unclear whether this assumption holds in practical problems. In this paper, we consider the general situation where both (X) and (Y jX) can change across all domains. We propose to learn a feature representation which has domain-invariant class conditional distributions (h(X)jY ). With the conditional invariant representation, the invariance of the joint distribution (h(X);Y ) can be guaranteed if the class prior (Y ) does not change across training and test domains. Extensive experiments on both synthetic and real data demonstrate the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Transform-invariant convolutional neural networks for image classification and search 24

Transform-invariant convolutional neural networks for image ...

引用

24th ACM Multimedia Conference, MM 2016

作者： Shen, Xu Tian, Xinmei He, Anfeng Sun, Shaoyan Tao, Dacheng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230027 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia

ISBN: (纸本)9781450336031

Convolutional neural networks (CNNs) have achieved stateof-the-art results on many visual recognition tasks. However, current CNN models still exhibit a poor ability to be invariant to spatial transformations of images. Intuitively, with sufficient layers and parameters, hierarchical combinations of convolution (matrix multiplication and nonlinear activation) and pooling operations should be able to learn a robust mapping from transformed input images to transform-invariant representations. In this paper, we propose randomly transforming (rotation, scale, and translation) feature maps of CNNs during the training stage. This prevents complex dependencies of specific rotation, scale, and translation levels of training images in CNN models. Rather, each convolutional kernel learns to detect a feature that is generally helpful for producing the transforminvariant answer given the combinatorially large variety of transform levels of its input feature maps. In this way, we do not require any extra training supervision or modification to the optimization process and training images. We show that random transformation provides significant improvements of CNNs on many benchmark tasks, including small-scale image recognition, large-scale image recognition, and image retrieval. © 2016 ACM.

关键词： Mathematical transformations

来源：评论

学校读者我要写书评

暂无评论

Circuit tolerance design by differential evolution with hybrid analysis method

Circuit tolerance design by differential evolution with hybr...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Fugui Zhong Bin Li Bo Yuan CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Hefei China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems USTC-Birmingham Joint Research Institute in Intelligent Computation and Its Applications (UBRI) University of Science and Technology of China Hefei China USTC-Birmingham Joint Research Institute in Intelligent Computation and Its Applications (UBRI) University of Science and Technology of China Hefei China

With the continued scaling down of electronic device dimensions, circuit design under parameter variations has received increasing interests. In this paper, a new method that combine the differential evolution with hybrid analysis method is presented to solve the worst-case circuit tolerance design problem. The hybrid analysis method is comprised of two commonly used worst-case circuit tolerance analysis approaches, vertex analysis and Monte Carlo analysis. The search direction of differential evolution is leaded by vertex analysis at the first stage, through which we can reduce the computational complexity of fitness calculation dramatically. Monte Carlo analysis, a higher accuracy analysis method, is applied to ensure the quality of the solutions at the second stage. Some of the individuals are reinitialized to enhance the diversity of the population at the beginning of the second stage. By cooperating the two analysis methods, the proposed method can converge to the global optimum or near-optimum solutions more quickly. The experiment results show the effectiveness and efficiency of proposed techniques for the circuit tolerance design.

关键词： Monte Carlo methods Algorithm design and analysis Sociology Uncertainty Upper bound Computational efficiency

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：