检索结果-内蒙古大学图书馆

Convergence analysis of nonconvex distributed stochastic zeroth-order coordinate method

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Shengjun Dong, Yunlong Xie, Dong Yao, Lisha Bailey, Colleen P. Fu, Shengli OSCAR Laboratory Department of Electrical Engineering University of North Texas DentonTX76207 United States School of Artificial Intelligence and Automation The MOE Key Laboratory of Image Processing and Intelligent Control The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China

This paper investigates the stochastic distributed nonconvex optimization problem of minimizing a global cost function formed by the summation of n local cost functions. We solve such a problem by involving zeroth-order (ZO) information exchange. In this paper, we propose a ZO distributed primal–dual coordinate method (ZODIAC) to solve the stochastic optimization problem. Agents approximate their own local stochastic ZO oracle along with coordinates with an adaptive smoothing parameter. We show that the proposed algorithm achieves the convergence rate of O(√p/√T) for general nonconvex cost functions. We demonstrate the efficiency of proposed algorithms through a numerical example in comparison with the existing state-of-the-art centralized and distributed ZO algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zeng, Wenzheng Xiao, Yang Wei, Sicheng Gan, Jinfang Zhang, Xintao Cao, Zhiguo Fang, Zhiwen Zhou, Joey Tianyi 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 School of Biomedical Engineering Southern Medical University Guangzhou510515 China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou510280 China Singapore Singapore

Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-person cases towards trimmed video. However, multi-person scenario within untrimmed videos is also important for practical applications, which has not been well concerned yet. To address this, we shed light on this research field for the first time with essential contributions on dataset, theory, and practices. In particular, a large-scale dataset termed MPEblink that involves 686 untrimmed videos with 8748 eyeblink events is proposed under multi-person conditions. The samples are captured from unconstrained films to reveal "in the wild" characteristics. Meanwhile, a real-time multi-person eyeblink detection method is also proposed. Being different from the existing counterparts, our proposition runs in a one-stage spatio-temporal way with end-to-end learning capacity. Specifically, it simultaneously addresses the sub-tasks of face detection, face tracking, and human instance-level eyeblink detection. This paradigm holds 2 main advantages: (1) eyeblink features can be facilitated via the face's global context (e.g., head pose and illumination condition) with joint optimization and interaction, and (2) addressing these sub-tasks in parallel instead of sequential manner can save time remarkably to meet the real-time running requirement. Experiments on MPEblink verify the essential challenges of real-time multi-person eyeblink detection in the wild for untrimmed video. Our method also outperforms existing approaches by large margins and with a high inference speed. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

Research on the detection method of alignment beacon based on the spatial structure feature of train bogies

学校读者我要写书评

暂无评论

Research on the detection method of alignment beacon based o...

Chinese Automation Congress (CAC)

作者： Chong Cao Shaowei Wan Gang Peng Dingxin He Sheng Zhong Zhang Deng Wentao Guo School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Beijing Railway Institute of Mechanical & Electrical Engineering Group Co. Ltd. Beijing China Wuhan Lisai Technology Co. Ltd. Wuhan China

The high-speed train inspection robot needs to perform alignment parking and image acquisition at the position of the train bogie, and reliable alignment identification marks are the basis for the inspection robot to achieve highprecision alignment parking. The existing alignment method is mainly based on the way of artificial beacons, in the inspection workshop through manual laying of additional identification marks such as QR codes, magnetic stripes, RFID electronic tags, auxiliary robot alignment parking, but this type of method in beacon maintenance, laying costs and other aspects have certain limitations. Aiming at the problem, this paper proposes a vision-based bogie beacon detection method, which combines the target detection technology with the unique bogie spatial structure feature of the train, and provides reliable identification marks for the alignment and parking of the inspection robot. This method improves the alignment accuracy, reduces the cost of laying and maintaining artificial beacons, and has high application value.

关键词： Shafts Costs Wheels Object detection Inspection Maintenance engineering Feature extraction

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB image

学校读者我要写书评

暂无评论

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D ...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Changlong Jiang Yang Xiao Cunlin Wu Mingyang Zhang Jinghong Zheng Zhiguo Cao Joey Tianyi Zhou 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 Alibaba Group Centre for Frontier AI Research Agency for Science Technology and Research (A*STAR) Singapore Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore

3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance patterns between 2 hands, ill-posed joint position mapping from 2D to 3D, etc.. To address these, we propose to extend A2J-the state-of-the-art depth-based 3D single hand pose estimation method-to RGB domain under interacting hand condition. Our key idea is to equip A2J with strong local-global aware ability to well capture interacting hands' local fine details and global articulated clues among joints jointly. To this end, A2J is evolved under Transformer's non-local encoding-decoding framework to build A2J- Transformer. It holds 3 main advantages over A2J. First, self-attention across local anchor points is built to make them global spatial context aware to better capture joints' articulation clues for resisting occlusion. Secondly, each anchor point is regarded as learnable query with adaptive feature learning for facilitating pattern fitting capacity, instead of having the same local representation with the others. Last but not least, anchor point locates in 3D space instead of 2D as in A2J, to leverage 3D pose prediction. Experiments on challenging InterHand 2.6M demonstrate that, A2J-Transformer can achieve state-of-the-art model-free performance (3.38mm MPJPE advancement in 2-hand case) and can also be applied to depth domain with strong generalization. The code is avaliable at https://***/ChanglongJiangGit/A2J-Transformer.

关键词：

SMTC-CL: Continuous Learning via Selective Multi-Task Coordination for Adaptive Signal Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Hao, Xiaoyang Yang, Shuyuan Liu, Ruoyu Feng, Zhixi Peng, Tongqing Huang, Bincheng Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence Xi'an710071 China Avic Xi'an Flight Automatic Control Research Institute China MeiTuan China China Electronics Technology Group Corporation Institute of Information Science and Technology China

Continuously adaptive signal classification in complex electromagnetic environments is a desired property of realistic intelligent systems. However, the limitation of most existing signal processing tasks and methods lies in their assumption of fixed categories and invariant distributions. In contrast, humans naturally acquire knowledge continuously from data streams, enhancing their capabilities through cross-task knowledge integration and learning from the past. Inspired by this, we propose a continuous learning (CL) method based on selective multi-task coordination (SMTC) to deal with ever-changing task categories and distributions in practical electromagnetic environments (denoted as SMTC-CL). Firstly, we propose a signal task distribution comparison (TDC) method that leverages intra-domain density and inter-domain divergence. TDC selectively activates multiple old tasks to collaboration with the current incremental new task. Secondly, we propose the SMTC method. By revisiting potential collaborative tasks from the past using TDC and formulating different selection strategies based on the context, continuous learners can achieve mutual benefits between past and current tasks in SMTC learning. SMTC can partially alleviate catastrophic forgetting and enable continuous learners to adapt to the changing electromagnetic environment. Based on the signal automatic modulation classification (AMC) and real-world specific emitter identification (SEI) datasets, extensive experimental results validate the effectiveness of our proposed method on a variety of CL scenarios, including varying signal task categories, distributions, and their combinations. © 2015 IEEE.

关键词： Contrastive Learning

Decentralized coordination between economic dispatch and demand response in multi-energy systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Zishun Zhu, Shanying Xu, Jinming Chen, Cailian The Department of Automation Shanghai Jiaotong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China College of Control Science and Engineering Zhejiang University HangzhouZhejiang310027 China

In this paper, we investigate the problem of coordination between economic dispatch (ED) and demand response (DR) in multi-energy systems (MESs), aiming to improve the economic utility and reduce the waste of energy in MESs. Since multiple energy sources are coupled through energy hubs (EHs), the supply-demand constraints are nonconvex. To deal with this issue, we propose a linearization method to transform the coordination problem to a convex social welfare optimization one. Then a decentralized algorithm based on parallel Alternating Direction Method of Multipliers (ADMM) and dynamic average tracking protocol is developed, where each agent could only make decisions based on information from their neighbors. Moreover, by using variational inequality and Lyapunov-based techniques, we show that our algorithm could always converge to the global optimal solution. Finally, a case study on the modified IEEE 14-bus network verifies the feasibility and effectiveness of our algorithm. Copyright © 2021, The Authors. All rights reserved.

关键词： Electric load dispatching

Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement

学校读者我要写书评

暂无评论

Watch the Speakers: A Hybrid Continuous Attribution Network ...

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Shanglin Lei Xiaoping Wang Guanting Dong Jiang Li Yingjian Liu 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 Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Institute of Artificial Intelligence Huazhong University of Science and Technology (HUST) Wuhan China

Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization to diverse scenarios due to insufficient modeling of context, ambiguous capture of dialogue relationships and overfitting in speaker modeling. In this work, we present a Hybrid Continuous Attributive Network (HCAN) to address these issues in the perspective of emotional continuation and emotional attribution. Specifically, HCAN adopts a hybrid recurrent and attention-based module to model global emotion continuity. Then a novel Emotional Attribution Encoding (EAE) is proposed to model intra- and inter-emotional attribution for each utterance. Moreover, aiming to enhance the robustness of the model in speaker modeling and improve its performance in different scenarios, A comprehensive loss function emotional cognitive loss $\mathcal{L}_{EC}$ is proposed to alleviate emotional drift and overcome the overfitting of the model to speaker modeling. Our model achieves state-of-the-art performance on three datasets, demonstrating the superiority of our work. Another extensive comparative experiments and ablation studies on three benchmarks are conducted to provided evidence to support the efficacy of each module. Further exploration of generalization ability experiments shows the plug-and-play nature of the EAE module in our method.

关键词：

Modelling brain based on canonical ensemble with functional MRI: A thermodynamic exploration on neural system

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Wei Zhou, Chenxi Yang, Bin Fan, Wenliang Chen, Xi School of Artificial Intelligence and Automation Huazhong University of Science and Technology WuhanHubei430074 China Image Processing and Intelligent Control Key Laboratory of the Education Ministry of China WuhanHubei430074 China Department of Radiology Union Hospital Tongji Medical College Huazhong University of Science and Technology WuhanHubei430074 China

Objective. Modelling is an important way to study the working mechanism of brain. While the characterization and understanding of brain are still inadequate. This study tried to build a model of brain from the perspective of thermodynamics at system level, which brought a new thinking to brain modelling. Approach. Regarding brain regions as systems, voxels as particles, and intensity of signals as energy of particles, the thermodynamic model of brain was built based on canonical ensemble theory. Two pairs of activated regions and two pairs of inactivated brain regions were selected for comparison in this study, and the analysis on thermodynamic properties based on the model proposed were performed. In addition, the thermodynamic properties were also extracted as input features for the detection of Alzheimer's disease. Main results. The experiment results verified the assumption that the brain also follows the thermodynamic laws. It demonstrated the feasibility and rationality of brain thermodynamic modelling method proposed, indicating that thermodynamic parameters could be applied to describe the state of neural system. Meanwhile, the brain thermodynamic model achieved much better accuracy in detection of Alzheimer's disease, suggesting the potential application of thermodynamic model in auxiliary diagnosis. Significance. (1) Instead of applying some thermodynamic parameters to analyze neural system, a brain model at system level was proposed from perspective of thermodynamics for the first time in this study. (2) The study discovered that the neural system also follows the laws of thermodynamics, which leads to increased internal energy, increased free energy and decreased entropy when system is activated. (3) The detection of neural disease was demonstrated to be benefit from thermodynamic model, implying the immense potential of thermodynamics in auxiliary *** Codes 80-10, 82-10, 92B99 Copyright © 2021, The Authors. All rights reserved.

关键词： Brain

Hybrid Data-Free Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students