检索结果-内蒙古大学图书馆

Double Backpropagation for Training Autoencoders against Adversarial Attack

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Sun, Chengjin Chen, Sizhe Huang, Xiaolin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing 800 Dongchuan Road Shanghai200240 China

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data storage and transmission, however, the current autoencoders are easily attacked, i.e., one can slightly modify an input but has totally different codes. The vulnerability is rooted the sensitivity of the autoencoders and to enhance the robustness, we propose to adopt double backpropagation (DBP) to secure autoencoder such as VAE and DRAW. We restrict the gradient from the reconstruction image to the original one so that the autoencoder is not sensitive to trivial perturbation produced by the adversarial attack. After smoothing the gradient by DBP, we further smooth the label by Gaussian Mixture Model (GMM), aiming for accurate and robust classification. We demonstrate in MNIST, CelebA, SVHN that our method leads to a robust autoencoder resistant to attack and a robust classifier able for image transition and immune to adversarial attack if combined with GMM. Copyright © 2020, The Authors. All rights reserved.

关键词： Gaussian distribution

CMCRD: Cross-Modal Contrastive Representation Distillation for Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kan, Siyuan Wu, Huanyu Cui, Zhenyao Huang, Fan Xu, Xiaolong Wu, Dongrui Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Wuhan Institute of Digital Engineering Wuhan430074 China Shanghai Jiao Tong University Shanghai200240 China

Emotion recognition is an important component of affective computing, and also human-machine interaction. Unimodal emotion recognition is convenient, but the accuracy may not be high enough;on the contrary, multi-modal emotion recognition may be more accurate, but it also increases the complexity and cost of the data collection system. This paper considers cross-modal emotion recognition, i.e., using both electroencephalography (EEG) and eye movement in training, but only EEG or eye movement in test. We propose cross-modal contrastive representation distillation (CMCRD), which uses a pre-trained eye movement classification model to assist the training of an EEG classification model, improving feature extraction from EEG signals, or vice versa. During test, only EEG signals (or eye movement signals) are acquired, eliminating the need for multi-modal data. CMCRD not only improves the emotion recognition accuracy, but also makes the system more simplified and practical. Experiments using three different neural network architectures on three multi-modal emotion recognition datasets demonstrated the effectiveness of CMCRD. Compared with the EEG-only model, it improved the average classification accuracy by about 6.2%. © 2025, CC BY.

关键词： Modal analysis

Graph-based scale-aware network for human parsing 1

学校读者我要写书评

暂无评论

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Yang, Beibei Yu, Changqian Liu, Jiahui Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Recent work has made considerable progress in exploring contextual information for human parsing with the Fully Convolutional Network framework. However, there still exist two challenges: (1) inherent relative relationships between parts;(2) scale variation of human parts. To tackle both problems, we propose a Graph-Based Scale-Aware Network for human parsing. First, we embed a Graph-Based Part Reasoning Layer into the backbone network to reason the relative relationship between human parts. Then we construct a Scale-Aware Context Embedding Layer, which consists of two branches to capture scale-specific contextual information, with different receptive fields and scale-specific supervisions. In addition, we adopt an edge supervision to further improve the performance. Extensive experimental evaluations demonstrate that the proposed model performs favorably against the state-of-the-art human parsing methods. More specifically, our algorithm achieves 53.32% (mIoU) on the LIP dataset. © Springer Nature Switzerland AG 2019.

关键词： Embeddings

Distributed second order sliding mode secondary frequency control for HVDC system

学校读者我要写书评

暂无评论

Distributed second order sliding mode secondary frequency co...

Chinese Automation Congress (CAC)

作者： Yang-Ming Dou Ming Chi Zhi-Wei Liu Key Laboratory of Image Processing and Intelligent Control Ministry of Education College of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

This paper studies the secondary frequency control among non-synchronous AC areas interconnected by High Voltage Direct Current (HVDC). A distributed second order sliding mode control scheme is adopted to secondary frequency control of HVDC transmission systems to adjust the frequency of power grid to rated value, which solves the frequency disturbance caused by load power change of the DC power grid. And on this basis, the power generation in each region is reasonably distributed, so as to minimize the cost of power generation. Finally, the stability of the system is proved on an appropriate sliding manifold.

关键词： Frequency control HVDC transmission Power system stability Economics Sliding mode control Power system dynamics Manifolds

A Multi-scale Network for Semantic Segmentation of 3D Point Clouds

学校读者我要写书评

暂无评论

A Multi-scale Network for Semantic Segmentation of 3D Point ...

Chinese Automation Congress (CAC)

作者： Ying He Li Xiao Yong Jiang Zhigang Sun Zhuo Wang Gang Peng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Semantic segmentation is a fundamental operation in scene analysis. In this paper, an effective multiscale network for 3D point cloud semantic segmentation was introduced. By using a multiscale local feature extraction module which composed of four feature extractors of different scales in parallel, the generalizability of network for complex structures is enhanced effectively. To adaptively learn important feature channels, an attention mechanism is designed. Combining multiple features through skip connection, the network can preferably assign the semantic label for every point by exploiting global and local features. Experiments on 3D dataset (S3DIS) verify that our network is able to learn local region features, and the results are superior or comparable to the state-of-the-art.

关键词： Feature extraction Three-dimensional displays Semantics Two dimensional displays Intelligent control image processing Automation

Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Ziang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

—In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling effort. It optimally selects the best few samples to label, so that a better machine learning model can be trained from the same number of labeled samples. This paper considers active learning for regression (ALR) problems. Three essential criteria – informativeness, representativeness, and diversity – have been proposed for ALR. However, very few approaches in the literature have considered all three of them simultaneously. We propose three new ALR approaches, with different strategies for integrating the three criteria. Extensive experiments on 12 datasets in various domains demonstrated their effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

Representative graph neural network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yu, Changqian Gao, Changxin Sang, Nong Yu, Changqian Liu, Yifan Shen, Chunhua Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science & Technology China University of Adelaide Australia

Non-local operation is widely explored to model the long-range dependencies. However, the redundant computation in this operation leads to a prohibitive complexity. In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy. Instead of propagating the messages from all positions, our RepGraph layer computes the response of one node merely with a few representative nodes. The locations of representative nodes come from a learned spatial offset matrix. The RepGraph layer is flexible to integrate into many visual architectures and combine with other operations. With the application of semantic segmentation, without any bells and whistles, our RepGraph network can compete or perform favourably against the state-of-the-art methods on three challenging benchmarks: ADE20K, Cityscapes, and PASCAL-Context datasets. In the task of object detection, our RepGraph layer can also improve the performance on the COCO dataset compared to the non-local operation. Code is available at https://***/RepGraph. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

A memristor-based generalization and differentiation circuit design and the application in recognition

学校读者我要写书评

暂无评论

A memristor-based generalization and differentiation circuit...

第三十九届中国控制会议

作者： Meijia Shang Xiaoping Wang Mian Li the School of Artificial Intelligence and Automation Huazhong University of Science and Technology IEEE the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China

The traditional Pavlov associative memory circuit realizes the law of learning and forgetting in classical conditioned reflex. In addition, the law of generalization and differentiation also belongs to classical conditioned reflex, so the process of associative memory can be more effectively simulated by adding generalization and differentiation theory on the basis of traditional associative memory. In this paper, a memristor-based circuit is designed to implement generalization and differentiation based on Pavlov associative memory. The circuit can be applied to simple classification recognition. Based on the features of objects as input, the output of the circuit is used as the classification result to achieve the function of classification and recognition. Finally,the accuracy of classification recognition on the generalization and differentiation circuit proposed in this paper can be verified by the simulation results in PSPICE.

关键词： Memristor generalization differentiation Pavlov associative memory recognition

Fault-Tolerant Consensus for Linear Singular Multi-Agent Systems with Dynamic Adaptive Event-Triggered Mechanism

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Jiang, Ping Chen, Jiejie Zeng, Zhigang Chen, Boshan The School of Computer Hubei PolyTechnic University Huangshi435000 China The School of Automation Huazhong University of Science and Technology Wuhan430074 China The College of Computer Science and Technology Hubei Normal University Huangshi435002 China The College of Mathematics and Statistics Hubei Normal University Huangshi435002 China The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China

The fault-tolerant consensus of linear singular multi-agent systems (SMASs) is studied in this paper. Firstly, a general dynamic adaptive event-triggered mechanism (ETM) is proposed, and its special cases include the existing dynamic ETM and static ETM. Then, based on this dynamic ETM, a new distributed dynamic adaptive event-triggered fault-tolerant controller (DAETFTC) is designed. Then the consensus problem is discussed for the linear SMASs via the proposed DAETFTC. Moreover, we establish novel sufficient conditions to ensure that all agents of the linear SMAS can reach consensus asymptotically. In addition, it is prove that Zeno behavior can be strictly excluded. Finally, the obtained results are simulated by a numerical example. © 2022, The Authors. All rights reserved.

关键词： Multi agent systems