检索结果-内蒙古大学图书馆

Learning from Noisy Labels with Coarse-to-Fine Sample Credibility Modeling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Tencent Shanghai China Tongji University Shanghai China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well . In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2022, CC BY.

关键词： Deep neural networks

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yan, Tingbing Zeng, Wenzheng Xiao, Yang Tong, Xingyu Tan, Bo Fang, Zhiwen Cao, Zhiguo 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 Singapore Singapore

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text description generated from large language models (LLM) that contain high-level human knowledge, to guide feature learning, in a global-local-global way. Particularly, during training, we design 2 prompts to gain global and local text descriptions of each action from an LLM. We first utilize the global text description to guide the skeleton encoder focus on informative joints (i.e.,global-tolocal). Then we build non-local interaction between local text and joint features, to form the final global representation (i.e., local-to-global). To mitigate the asymmetry issue between the training and inference phases, we further design a dual-branch architecture that allows the model to perform novel class inference without any text input, also making the additional inference cost neglectable compared with the base skeleton encoder. Extensive experiments on three different benchmarks show that CrossGLG consistently outperforms the existing SOTA methods with large margins, and the inference cost (model size) is only 2.8% than the previous SOTA. CrossGLG can also serve as a plug-and-play module that can substantially enhance the performance of different SOTA skeleton encoders with a neglectable cost during inference. The source code will be released soon. © 2024, CC BY.

关键词： Signal encoding

Model-Based and Data-Driven Contingency Filtering for Real-Time Corrective Security-Constrained Economic Dispatch

学校读者我要写书评

暂无评论

Model-Based and Data-Driven Contingency Filtering for Real-T...

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Donghai Han Yaowen Yu Dingxin He Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665434263

Security-constrained economic dispatch (SCED) is one of the most important problems in power system operations. Corrective SCED (CSCED) is a type of SCED that considers corrective capabilities of the power system and adjusts base case decisions according to post-contingency states. Because of the large scale of the CSCED problem, it is difficult for purely model-based approaches to meet the time limits in real-time practical operations. To leverage historical operation data, this paper develops a novel hybrid model-based and data-driven framework to accelerate the solution process of CSCED. In the offline stage, our previous model-based contingency filtering approach is utilized to label active statuses of contingencies against historical net load samples. In the online stage, a multi-label classifier based on the K-Nearest Neighbor (KNN) algorithm quickly generates an active contingency set corresponding to the real-time net load. This active contingency set can be used to calculate the economic dispatch decisions in one shot. In addition, the accuracy of our framework can be further improved by adding an optional contingency filtering procedure at the end. Numerical testing results on the IEEE RTS-96 system demonstrate the accuracy and computational efficiency of the hybrid framework as compared to a purely model-based approach.

关键词： Economics Renewable energy sources Filtering Computational modeling System integration Real-time systems Numerical models

6-DOF grasp planning of manipulator combined with self-supervised learning

学校读者我要写书评

暂无评论

6-DOF grasp planning of manipulator combined with self-super...

第33届中国控制与决策会议

作者： Zhenyu Ren Gang Peng Jin Yang Hao Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education

To realize a robust robotic grasping system for unknown objects in an unstructured environment,large amounts of grasp data and 3D model data for the object are *** reduce the time cost of data acquisition and labeling and increase the rate of successful grasps,we developed a self-supervised learning mechanism to control grasp tasks performed by ***,a manipulator automatically collects the point cloud for the objects from multiple perspectives to increase the efficiency of data *** complete point cloud for the objects is obtained by utilizing the hand-eye vision of the manipulator,and the TSDF ***,the point cloud data for the objects is used to generate a series of six-degrees-of-freedom grasp poses,and the force-closure decision algorithm is used to add the grasp quality label to each grasp pose to realize the automatic labeling of grasp ***,the point cloud in the gripper closing area corresponding to each grasp pose is obtained;it is then used to train the grasp-quality classification model for the *** results of performing actual grasping experiments demonstrate that the proposed self-supervised learning method can increase the rate of successful grasps for the manipulator.

关键词： Manipulator Grasping Self-Supervised Learning 3D Reconstruction

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

arXiv 2023年

作者： Lei, Shanglin Wang, Xiaoping Dong, Guanting Li, Jiang Liu, Yingjian School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China Wuhan430074 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 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 LEC 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. © 2023, CC BY-SA.

关键词： Emotion Recognition

Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qing, Zhiwu Zhang, Shiwei Huang, Ziyuan Xu, Yi Wang, Xiang Tang, Mingqian Gao, Changxin Jin, Rong 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 Dalian Unversity of Technology China

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited performance gain. In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos. To this end, we propose to learn a hierarchy of consistencies in videos, i.e., visual consistency and topical consistency, corresponding respectively to clip pairs that tend to be visually similar when separated by a short time span and share similar topics when separated by a long time span. Specifically, a hierarchical consistency learning framework HiCo is presented, where the visually consistent pairs are encouraged to have the same representation through contrastive learning, while the topically consistent pairs are coupled through a topical classifier that distinguishes whether they are topic-related. Further, we impose a gradual sampling algorithm for proposed hierarchical consistency learning, and demonstrate its theoretical superiority. Empirically, we show that not only HiCo can generate stronger representations on untrimmed videos, it also improves the representation quality when applied to trimmed videos. This is in contrast to standard contrastive learning that fails to learn appropriate representations from untrimmed videos. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Deep transfer learning-based decoder calibration for intracortical brain-machine interfaces

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2025年第Pt A期192卷 110231-110231页

作者： Li, Xiao Dong, Xianxin Wang, Jun Mao, Haodong Tu, Xikai Li, Wei He, Jiping Li, Qiang Zhang, Peng Hubei Key Laboratory of Modern Manufacturing Quantity Engineering School of Mechanical Engineering Hubei University of Technology Wuhan430068 China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Science and Technology Hubei Wuhan China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan China Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

Intracortical brain-machine interfaces (iBMIs) aim to establish a communication path between the brain and external devices. However, in the daily use of iBMIs, the non-stationarity of recorded neural signals necessitates frequent recalibration of the iBMI decoder to maintain decoding performance, which requires collecting and labeling a large amount of new data. To address this challenge and minimize the time needed for decoder recalibration, we proposed an active learning domain adversarial neural network (AL-DANN). This model leveraged a substantial volume of historical data alongside a small amount of current data (four samples per category) to calibrate the decoder. By incorporating domain adversarial and active learning strategies, the model effectively transferred knowledge from historical data to new data, reducing the demand for new samples. We validated the proposed method using neural signals recorded from three monkeys performing different movements in a classification task or a regression task. The results showed that the AL-DANN outperformed existing state-of-the-art methods. Impressively, it required only four new samples per category for decoder recalibration, leading to a recalibration time reduction of over 80 %. To our knowledge, this is the first study to incorporate deep transfer learning into iBMI decoder calibration, highlighting the significant potential of applying deep learning technologies in iBMIs. © 2025

关键词： Adversarial machine learning

A Novel YJQR-LSTM Model for Nonparametric Probabilistic Sustainable Agriculture Wind Power Forecasting Based on intelligent IoT

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2024年

作者： Wang, Jie Jiang, Junhui Chen, Xinlong Cai, Defu Wu, Yue Lu, Renzhi School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Harbin Engineering University College of Computer Science and Technology Harbin150001 China State Grid Hubei Electric Power Research Institute Hubei Wuhan430079 China School of Technology State Key Laboratory of Efficient Production of Forest Resources Key Laboratory of National Forestry and Grassland Administration on Forestry Equipment and Automation Beijing Forestry University Beijing100083 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing400065 China State Key Laboratory of Mechanical Transmission for Advanced Equipment Chongqing University Chongqing400044 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

Energy costs associated with the consumption of non-renewable energy sources have become an important issue in improving the international competitiveness of agriculture. Wind power, as a renewable energy source, can replace non-renewable energy sources to reduce energy costs and improve the sustainability of agricultural. However, the inherent intermittency, randomness, and volatility within weather conditions and wind speed presents a substantial challenge in accurately predicting wind power generation. This work proposes a novel YJQR-LSTM algorithm that leverages Yeo-Johnson quantile regression (YJQR) with a long short-term memory (LSTM) network for nonparametric probabilistic forecasting of wind power generation via the intelligent Internet of Things. First, an improved YJQR model based on the YJ transformation is designed to obtain a more precise characterization of wind uncertainty, providing a more flexible probability density function for wind power generation. Then, utilizing the unique structure of the LSTM network to learn the parameters of the YJQR model, temporal features can be extracted from time series data. To mitigate the impact of outliers in the raw data on accuracy and improve computational efficiency, a novel logarithmic likelihood function is developed as the loss function utilized in the training phase. The effectiveness of the proposed algorithm is validated using a real-world dataset from five wind farms from the Global Energy Forecasting Competition. Numerical results demonstrate that the algorithm provides more accurate wind power prediction results in complex wind power data environments, which is important for making full use of wind energy and thus reducing the consumption of non-renewable energy in agriculture. © 2024 IEEE.

关键词： Wind forecasting

Sample Weighted Gradient Regularization for Source-Free Domain Adaptation

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Long, Yunchong Xu, Bingrong Zhang, Qingyong Yin, Jianhua Zeng, Zhigang School of Automation Wuhan University of Technology Wuhan430070 China Intelligent Transportation Systems Research Center Wuhan University of Technology Wuhan430063 China The Engineering Research Center of Transportation Information and Safety Ministry of Education Wuhan430063 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China

Conventional Domain Adaptation(DA) algorithms typically rely on access to the source data,which may not always be practical due to privacy concerns or limited storage *** address these challenges,Source-Free Domain Adaptation(SFDA) has emerged as an alternative that relies solely on a pre-trained source model rather than the actual source *** SFDA,pseudo-label supervised learning is commonly employed and initially plays a significant role in enhancing model performance during the early stages of target domain ***,as adaptation progresses,the performance can stagnate or even deteriorate due to the noise inherent in pseudo-labels,a phenomenon known as Confirmation *** noise present in target domain pseudo-labels introduces additional uncertainty and overfitting risks to the *** this study,a novel framework named Sample Weighted Gradient Regularization (SWGR) was introduced to tackle this *** first propose the Label Uncertainty Estimation Metric (LUEM),a reweighting strategy that assesses the reliability of *** metric evaluates label uncertainty from both the source domain pre-trained model and spatial distribution of target domain samples,allowing the model to achieve improved cross-domain transfer performance with high-confidence samples in the target domain. Additionally,we impose a constraint on the gradient descent process of the total loss function in the form of an inequality to prevent entropy from *** Gradient Regularization eliminates overfitting while also guiding the model in lowering prediction uncertainty *** approach reduces the uncertainty in the target domain and enhances the model's generalization *** results demonstrate that our method surpasses competing SFDA approaches and even outperforms many traditional DA methods which require extensive amounts of source domain data. © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning