检索结果-内蒙古大学图书馆

NPGA: A Unified Algorithmic Framework for Decentralized Constraint-Coupled Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jingwang Su, Housheng School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

This work focuses on a class of general decentralized constraint-coupled optimization problems. We propose a novel nested primal-dual gradient algorithm (NPGA), which can achieve linear convergence under the weakest known condition, and its theoretical convergence rate surpasses all known results. More importantly, NPGA serves not only as an algorithm but also as a unified algorithmic framework, encompassing various existing algorithms as special cases. By designing different network matrices, we can derive numerous versions of NPGA and analyze their convergences by leveraging the convergence results of NPGA conveniently, thereby enabling the design of more efficient algorithms. Finally, we conduct numerical experiments to compare the convergence rates of NPGA and existing algorithms, providing empirical evidence for the superior performance of NPGA. Copyright © 2022, The Authors. All rights reserved.

关键词： Consensus algorithm

Learning to Learn Transferable Generative Attack for Person Re-Identification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan The College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan Changsha China The College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha China

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 21.5% and 11.3% on mean mAP drop rate, respectively. The code of MTGA will be released after the paper is accepted. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

Implicit Tracking-Based Distributed Constraint-Coupled Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jingwang Su, Housheng The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

A class of distributed optimization problem with a globally coupled equality constraint and local constrained sets is studied in this paper. For its special case where local constrained sets are absent, an augmented primal-dual gradient dynamics is proposed and analyzed, but it cannot be implemented distributedly since the violation of the coupled constraint needs to be used. Benefiting from the brand-new comprehending of a classical distributed unconstrained optimization algorithm, the novel implicit tracking approach is proposed to track the violation distributedly, which leads to the birth of the implicit tracking-based distributed augmented primal-dual gradient dynamics (IDEA). A projected variant of IDEA, i.e., Proj-IDEA, is further designed to deal with the general case where local constrained sets exist. With the aid of the Lyapunov stability theory, the convergences of IDEA and Proj-IDEA over undigraphs and digraphs are analyzed respectively. As far as we know, Proj-IDEA is the first constant step-size distributed algorithm which can solve the studied problem without the need of the strict convexity of local cost functions. Besides, if local cost functions are strongly convex and smooth, IDEA can achieve exponential convergence with a weaker condition about the coupled constraint. Finally, numerical experiments are taken to corroborate our theoretical results. © 2022, CC BY.

关键词： Cost functions

A Hybrid Wind Power Prediction Model Based on Seasonal Feature Decomposition and Enhanced Feature Extraction

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Weipeng Chong, Yuting Guo, Xin Liu, Jun School of Automation and Information Engineering Xi’an University of Technology No. 5 Jinhua South Road Shaanxi Xi’an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing No. 5 Jinhua South Road Shaanxi Xi’an710048 China

Efficient and accurate wind power prediction is crucial for enhancing the reliability and safety of power system operation and management. The integration of advanced data-driven forecasting methods with precise and efficient data feature decomposition and extraction techniques is necessary to improve the accuracy of wind power generation prediction, due to the inherent randomness and nonlinearity of physical states impacting wind power output, as well as the abundance of redundant information in their original measurement data. This paper proposes a novel hybrid wind power prediction model based on seasonal feature decomposition of wind energy data and enhanced feature extraction. Its effectiveness and superiority are demonstrated through comprehensive multi-model comparisons. © 2024, The Authors. All rights reserved.

关键词： Wind power

GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Jiang Wang, Xiaoping Lv, Guoqing Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Emotion Recognition in Conversation (ERC) plays a significant part in Human-Computer Interaction (HCI) systems since it can provide empathetic services. Multimodal ERC can mitigate the drawbacks of uni-modal approaches. Recently, Graph Neural Networks (GNNs) have been widely used in a variety of fields due to their superior performance in relation modeling. In multimodal ERC, GNNs are capable of extracting both long-distance contextual information and inter-modal interactive information. Unfortunately, since existing methods such as MMGCN directly fuse multiple modalities, redundant information may be generated and diverse information may be lost. In this work, we present a directed Graph based Cross-modal Feature Complementation (GraphCFC) module that can efficiently model contextual and interactive information. GraphCFC alleviates the problem of heterogeneity gap in multimodal fusion by utilizing multiple subspace extractors and Pair-wise Cross-modal Complementary (PairCC) strategy. We extract various types of edges from the constructed graph for encoding, thus enabling GNNs to extract crucial contextual and interactive information more accurately when performing message passing. Furthermore, we design a GNN structure called GAT-MLP, which can provide a new unified network framework for multimodal learning. The experimental results on two benchmark datasets show that our GraphCFC outperforms the state-of-the-art (SOTA) approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Emotion Recognition

Lithium-ion battery state-of-charge estimation using a real-time moving horizon estimation algorithm

学校读者我要写书评

暂无评论

Lithium-ion battery state-of-charge estimation using a real-...

2021 CAA Symposium on Fault Detection, Supervision, and Safety for Technical Processes, SAFEPROCESS 2021

作者： Yan, Jiayu Li, Song Wan, Yiming Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China 29th Research Institute of China Electronics Technology Group Corporation Chengdu China

ISBN: (纸本)9781665401159

For battery management systems, it is significant to reliably estimate state-of-charge (SOC) from limited measurements in real time. Based on a nonlinear SOC-dependent equivalent circuit model, we propose a real-time moving horizon estimation (MHE) algorithm for SOC estimation. For efficient computation, the sequential quadratic programming strategy is applied, and each quadratic programming (QP) iteration is solved via the structure-exploiting forward and backward recursions. To account for the limited computation time allowed within each sampling interval, the proposed algorithm does not fully solve the receding horizon optimization problem over each sliding window, but performs fixed number of QP iterations. The simulation results show that compared to the existing fully solved MHE applied to SOC estimation, the proposed real-time MHE algorithm significantly saves computation time at the cost of a slight loss of estimation performance. © 2021 IEEE.

关键词： Quadratic programming

Multimodal Representations Learning Based on Mutual information Maximization and Minimization and Identity Embedding for Multimodal Sentiment Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zheng, Jiahao Zhang, Sen Wang, Xiaoping Zeng, Zhigang School of Artificial Intelligence and Automation The Key Laboratory of Image Processing Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan430074 China

Multimodal sentiment analysis (MSA) is a fundamental complex research problem due to the heterogeneity gap between different modalities and the ambiguity of human emotional expression. Although there have been many successful attempts to construct multimodal representations for MSA, there are still two challenges to be addressed: 1) A more robust multimodal representation needs to be constructed to bridge the heterogeneity gap and cope with the complex multimodal interactions, and 2) the contextual dynamics must be modeled effectively throughout the information flow. In this work, we propose a multimodal representation model based on Mutual information Maximization and Minimization and Identity Embedding (MMMIE). We combine mutual information maximization between modal pairs, and mutual information minimization between input data and corresponding features to mine the modal-invariant and task-related information. Furthermore, Identity Embedding is proposed to prompt the downstream network to perceive the contextual information. Experimental results on two public datasets demonstrate the effectiveness of the proposed model. Copyright © 2022, The Authors. All rights reserved.

关键词： Sentiment analysis

GNet: 3D Object Detection from Point Cloud with Geometry-Aware Network

学校读者我要写书评

暂无评论

GNet: 3D Object Detection from Point Cloud with Geometry-Awa...

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Hao Ruan Bingrong Xu Junbin Gao Lianguang Liu Junting Lv Yin Sheng Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China School of Automation Wuhan University of Technology Wuhan China

3D object detection based on point clouds in real-world applications has been a challenging task because the raw point cloud may be sparse or occluded. It may be caused by bad weather or limited sensor resolution, leading to decreasing detection performance. To this end, a novel highperformance Geometry-aware Network (GNet) is proposed and used to accurately detect 3D objects from sparse point clouds. Different from previous work that only regresses the offset of 3D bounding boxes numerically between ground truth (GT) and prediction, GNet considers the geometric information of 3D bounding boxes and combines the two effectively to achieve a better regression performance. In particular, Point Nets blocks learned voxel-wise features and the proposals are generated by the 3D voxel convolution neural network (voxel CNN). By utilizing the prior knowledge and the geometric properties of the 3D bounding boxes, the proposed novel OS-loss can improve detection performance and accelerate speed of inference. Furthermore, GNet takes advantage of prior geometry properties rather than only regressing the offset numerically. These speed up the convergence of the regression network. Finally, our proposed GNet was evaluated on the KITTI dataset for 3D objects and Bird’s Eye View (BEV) detection aspects. The results demonstrate that GNet can improve object detection performance for sparse point clouds.

关键词： Point cloud compression Location awareness Geometry Three-dimensional displays Neural networks Object detection Proposals

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

学校读者我要写书评

暂无评论

Frontiers of information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning