检索结果-内蒙古大学图书馆

Consensus-Based Distributed Algorithm for Gep

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Lv, Kexin He, Fan Huang, Xiaolin Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University MOE Key Laboratory of System Control and Information Processing Shanghai200240 China

Generalized eigenvalue problem (GEP) plays a significant role in signal processing and machine learning. This paper proposes a consensus-based distributed algorithm for GEP in multi-agent systems, where data samples are distributively stored across agents. The distributed GEP is reformulated as a consensus optimization, but the presence of its quadratic inseparable constraint makes the considered problem more challenging. To deal with it, a sequential method is proposed combined with the alternating direction method of multipliers, which requires communication between couples of nodes. Theoretical analysis shows the proposed algorithm will converge to the set of stationary solutions. And the numerical experiments on synthetic and real-world datasets validate that the approximated solution is competitive to the ground truth. © 2022, The Authors. All rights reserved.

关键词： Multi agent systems

MVCNet: Multi-View Contrastive Network for Motor imagery Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Ziwei Li, Siyang Chen, Xiaoqing Li, Wei 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 Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518000 China

Electroencephalography (EEG)-based brain-computer interfaces (BCIs) enable neural interaction by decoding brain activity for external communication. Motor imagery (MI) decoding has received significant attention due to its intuitive mechanism. However, most existing models rely on single-stream architectures and overlook the multi-view nature of EEG signals, leading to limited performance and generalization. We propose a multi-view contrastive network (MVCNet), a dual-branch architecture that parallelly integrates CNN and Transformer models to capture both local spatial-temporal features and global temporal dependencies. To enhance the informativeness of training data, MVCNet incorporates a unified augmentation pipeline across time, frequency, and spatial domains. Two contrastive modules are further introduced: a cross-view contrastive module that enforces consistency of original and augmented views, and a cross-model contrastive module that aligns features extracted from both branches. Final representations are fused and jointly optimized by contrastive and classification losses. Experiments on five public MI datasets across three scenarios demonstrate that MVCNet consistently outperforms seven state-of-the-art MI decoding networks, highlighting its effectiveness and generalization ability. MVCNet provides a robust solution for MI decoding by integrating multi-view information and dual-branch modeling, contributing to the development of more reliable BCI systems. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

Low-Rank Optimal Transport for Robust Domain Adaptation

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第7期11卷 1667-1680页

作者： Bingrong Xu Jianhua Yin Cheng Lian Yixin Su Zhigang Zeng IEEE the School of Automation Wuhan University of TechnologyWuhan 430070China Intelligent Transportation Systems Research Center Wuhan University of TechnologyWuhan 430063 Chongqing Research Institute Wuhan University of TechnologyChongqingChina the School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan 430074China

When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot of success both in theory and practice under the assumption that all the examples in the source domain are welllabeled and of high quality. However, the methods consistently lose robustness in noisy settings where data from the source domain have corrupted labels or features which is common in reality. Therefore, robust domain adaptation has been introduced to deal with such problems. In this paper, we attempt to solve two interrelated problems with robust domain adaptation:distribution shift across domains and sample noises of the source domain. To disentangle these challenges, an optimal transport approach with low-rank constraints is applied to guide the domain adaptation model training process to avoid noisy information influence. For the domain shift problem, the optimal transport mechanism can learn the joint data representations between the source and target domains using a measurement of discrepancy and preserve the discriminative information. The rank constraint on the transport matrix can help recover the corrupted subspace structures and eliminate the noise to some extent when dealing with corrupted source data. The solution to this relaxed and regularized optimal transport framework is a convex optimization problem that can be solved using the Augmented Lagrange Multiplier method, whose convergence can be mathematically proved. The effectiveness of the proposed method is evaluated through extensive experiments on both synthetic and real-world datasets.

关键词： Domain adaptation low-rank constraint noise corruption optimal transport

Spatial Distillation based Distribution Alignment (SDDA) for Cross-Headset EEG Classification

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Dingkun Li, Siyang Wang, Ziwei Li, Wei 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 Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518000 China

A non-invasive brain-computer interface (BCI) enables direct interaction between the user and external devices, typically via electroencephalogram (EEG) signals. However, decoding EEG signals across different headsets remains a significant challenge due to differences in the number and locations of the electrodes. To address this challenge, we propose a spatial distillation based distribution alignment (SDDA) approach for heterogeneous cross-headset transfer in non-invasive BCIs. SDDA uses first spatial distillation to make use of the full set of electrodes, and then input/feature/output space distribution alignments to cope with the significant differences between the source and target domains. To our knowledge, this is the first work to use knowledge distillation in cross-headset transfers. Extensive experiments on six EEG datasets from two BCI paradigms demonstrated that SDDA achieved superior performance in both offline unsupervised domain adaptation and online supervised domain adaptation scenarios, consistently outperforming 10 classical and state-of-the-art transfer learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Transfer learning

Disentangling Spatial and Temporal Learning for Efficient image-to-Video Transfer Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qing, Zhiwu Zhang, Shiwei Huang, Ziyuan Zhang, Yingya Gao, Changxin Zhao, Deli Sang, Nong Key Laboratory of Image Processing Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China ARC National University of Singapore Singapore

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pretraining on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://***/alibaba-mmai-research/DiST. Copyright © 2023, The Authors. All rights reserved.

关键词： Backpropagation

VideoLCM: Video Latent Consistency Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Zhang, Han Liu, Yu Zhang, Yingya Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Shanghai Jiao Tong University China

Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models. However, the consi...

关键词：

A Physiological Signal Emotion Recognition Method Based on Domain Adaptation and Incremental Learning

学校读者我要写书评

暂无评论

A Physiological Signal Emotion Recognition Method Based on D...

Cyber-Energy Systems and Intelligent Energy (ICCSIE), International Conference on

作者： Junnan Li Xiaoping Wang the School of Artificial Intelligence and Automation and the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan P. R. China

Temporal concept shift (TCS) is an unavoidable problem in physiological signal-based emotion recognition tasks, i.e., the data distribution of physiological signals is constantly changing over time, which gradually degrades the model accuracy. To this end, we propose a method based on a combination of domain adaptation and incremental learning to reduce the impact of temporal concept drift. In this paper, domain adaptation is used to reduce the distribution differences and incremental learning is used to prevent the learned knowledge from being forgotten. Finally, we validate the effectiveness of our approach on two real datasets.

关键词：

3D Cinemagraphy from a Single image

学校读者我要写书评

暂无评论

3D Cinemagraphy from a Single Image

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xingyi Li Zhiguo Cao Huiqiang Sun Jianming Zhang Ke Xian Guosheng Lin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology S-Lab Nanyang Technological University Adobe Research

We present 3D Cinemagraphy, a new technique that mar-ries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emer-gence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthe-size novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method.

关键词：

Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Xiaoqing Wang, Ziwei Wu, Dongrui The Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China

Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security. Although many adversarial defense approaches have been proposed in other application domains such as computer vision, previous research showed that their direct extensions to BCIs degrade the classification accuracy on benign samples. This phenomenon greatly affects the applicability of adversarial defense approaches to EEG-based BCIs. To mitigate this problem, we propose alignment-based adversarial training (ABAT), which performs EEG data alignment before adversarial training. Data alignment aligns EEG trials from different domains to reduce their distribution discrepancies, and adversarial training further robustifies the classification boundary. The integration of data alignment and adversarial training can make the trained EEG classifiers simultaneously more accurate and more robust. Experiments on five EEG datasets from two different BCI paradigms (motor imagery classification, and event related potential recognition), three convolutional neural network classifiers (EEGNet, ShallowCNN and DeepCNN) and three different experimental settings (offline within-subject cross-block/-session classification, online cross-session classification, and pre-trained classifiers) demonstrated its effectiveness. It is very intriguing that adversarial attacks, which are usually used to damage BCI systems, can be used in ABAT to simultaneously improve the model accuracy and robustness. © 2024, CC BY.

关键词： Adversarial machine learning