检索结果-内蒙古大学图书馆

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

Multi-View Contrastive Network (MVCNet) 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

Objective: An electroencephalography (EEG)-based brain-computer interface (BCI) serves as a direct communication pathway between the human brain and an external device. While supervised learning has been extensively explored for motor imagery (MI) EEG classification, small data quantity has been a key factor limiting the performance of deep feature learning. Methods: This paper proposes a knowledge-driven time-space-frequency based multi-view contrastive network (MVCNet) for MI EEG decoding in BCIs. MVCNet integrates knowledge from the time, space, and frequency domains into the training process through data augmentations from multiple views, fostering more discriminative feature learning of the characteristics of EEG data. We introduce a cross-view contrasting module to learn from different augmented views and a cross-model contrasting module to enhance the consistency of features extracted between knowledge-guided and data-driven models. Results: The combination of EEG data augmentation strategies was systematically investigated for more informative supervised contrastive learning. Experiments on four public MI datasets and three different architectures demonstrated that MVCNet outperformed 10 existing approaches. Significance: Our approach can significantly boost EEG classification performance beyond designated networks, showcasing the potential to enhance the feature learning process for better EEG decoding. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

Global Consensus for Heterogeneous Saturated Multi-Agent Systems via Sampled-Data control 63

学校读者我要写书评

暂无评论

Global Consensus for Heterogeneous Saturated Multi-Agent Sys...

63rd IEEE Conference on Decision and control, CDC 2024

作者： Qian, Juan Wang, Xiaoling Astolfi, Daniele Su, Housheng Jiang, Guo-Ping Nanjing University of Posts and Telecommunications College of Automation and the College of Artificial Intelligence Nanjing210023 China Nanjing210023 China Université Claude Bernard Lyon 1 Cnrs Lagepp Umr 5007 43 boulevard du 11 novembre 1918 VilleurbanneF-69100 France East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Huazhong University of Science and Technology School of Artificial Intelligence and Automation Image Processing and Intelligent Control Key Laboratory of Education Ministry of China Luoyu Road 1037 Wuhan430074 China

ISBN: (纸本)9798350316339

This paper addresses the global consensus problem for multi-input multi-output saturated systems within a sampled-data framework, aiming to advance global consensus, manage heterogeneous actuator saturation across components, and preserve distributed characteristics by using sampled-data feedback. We propose a distributed control algorithm that incorporates a redesigned saturation function, represented as decentralized dynamic saturation levels. These levels for each agent's dimensions are autonomously updated through an adaptive strategy, which mitigates heterogeneous saturation by carefully selecting constant and time-varying saturation parameters in it. Lyapunov analysis proves that global consensus can be achieved under the proposed control law, provided the sampling periods of all agents remain below a calculated threshold. An example is given to demonstrate the effectiveness of this approach. © 2024 IEEE.

关键词： Decentralized control

Deterministic-like data-driven discovery of stochastic differential equations via the Feynman–Kac formalism

学校读者我要写书评

暂无评论

The European Physical Journal Special Topics 2024年 1-21页

作者： Ma, Chaoxiang Huang, Cheng Cheng, Cheng Li, Xiuting The College of Informatics Huazhong Agriculture University and the China–Poland Belt and Road Joint Laboratory on Measurement and Control Technology Huazhong University of Science and Technology Wuhan People’s Republic of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Ministry of Education Key Lab of Intelligent Control and Image Processing Wuhan China

This paper develops a data-driven deterministic identification architecture for discovering stochastic differential equations (SDEs) directly from data. The architecture first generates deterministic data for stochastic processes using the Feynman–Kac formula, and gives a parabolic partial differential equation (PDE) associated with the SDE. Then, a sparse regression model is proposed to discover drift and diffusion terms in SDEs using PDE data-driven techniques, where a large candidate library of potential terms only for the drift and diffusion coefficients in SDEs need be constructed. To simultaneously infer the drift and diffusion terms, we proposed a sequential thresholded reweighted least-squares algorithm to solve the constructed sparse regression model. The main advantage of the proposed method is that on the one hand, theoretical and numerical identification results of PDEs can be used for SDEs, on the score, our SDE identification problem is translated into the parameter estimation problem of PDEs, on the other hand, the proposed algorithm is easily executed and can enhance the sparsity and accuracy. Through several classical SDEs and ordinary differential equations, the effectiveness of the proposed data-driven method is demonstrated, and several comparison experiments with state-of-the-art approaches is provided to illustrate the superiority of the developed algorithm.

关键词：

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：