检索结果-内蒙古大学图书馆

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

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

来源：评论

学校读者我要写书评

暂无评论

Lite-HRNet: A lightweight high-resolution network

arXiv

引用

arXiv 2021年

作者： Yu, Changqian Xiao, Bin Gao, Changxin Yuan, Lu Zhang, Lei Sang, Nong Wang, Jingdong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Microsoft

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet. We find that the heavily-used pointwise (1 × 1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1 × 1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1 × 1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner. The code and models have been publicly available at https://***/HRNet/Lite-HRNet. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

CPTNet: Cascade Pose Transform Network for Single image Talking Head Animation 15th

CPTNet: Cascade Pose Transform Network for Single Image Talk...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Jiale Xian, Ke Liu, Chengxin Chen, Yinpeng Cao, Zhiguo Zhong, Weicai 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 Huawei CBG Consumer Cloud Service Search Product and Big Data Platform Department Xi’an China

ISBN: (纸本)9783030695378

We study the problem of talking head animation from a single image. Most of the existing methods focus on generating talking heads for human. However, little attention has been paid to the creation of talking head anime. In this paper, our goal is to synthesize vivid talking heads from a single anime image. To this end, we propose cascade pose transform network, termed CPTNet, that consists of a face pose transform network and a head pose transform network. Specifically, we introduce a mask generator to animate facial expression (e.g., close eyes and open mouth) and a grid generator for head movement animation, followed by a fusion module to generate talking heads. In order to handle large motion and obtain more accurate results, we design a pose vector decomposition and cascaded refinement strategy. In addition, we create an anime talking head dataset, that includes various anime characters and poses, to train our model. Extensive experiments on our dataset demonstrate that our model outperforms other methods, generating more accurate and vivid talking heads from a single anime image. © 2021, Springer Nature Switzerland AG.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEEP NEURAL NETWORKS 8

EMPIRICAL STUDIES ON THE PROPERTIES OF LINEAR REGIONS IN DEE...

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Zhang, Xiao 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 Wuhan China

A deep neural network (DNN) with piecewise linear activations can partition the input space into numerous small linear regions, where different linear functions are fitted. It is believed that the number of these regions represents the expressivity of the DNN. This paper provides a novel and meticulous perspective to look into DNNs: Instead of just counting the number of the linear regions, we study their local properties, such as the inspheres, the directions of the corresponding hyperplanes, the decision boundaries, and the relevance of the surrounding regions. We empirically observed that different optimization techniques lead to completely different linear regions, even though they result in similar classification accuracies. We hope our study can inspire the design of novel optimization techniques, and help discover and analyze the behaviors of DNNs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cooperative Label-Free Moving Target Fencing for Second-Order Multi-Agent Systems with Rigid Formation

arXiv

引用

arXiv 2023年

作者： Hu, Bin-Bin Zhang, Hai-Tao Shi, Yang School of Artificial Intelligence Automation Key Laboratory of Image Processing Intelligent Control State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada

This paper proposes a label-free controller for a second-order multi-agent system to cooperatively fence a moving target of variational velocity into a convex hull formed by the agents whereas maintaining a rigid formation. Therein, no label is predetermined for a specified agent. To attain a rigid formation with guaranteed collision avoidance, each controller consists of two terms: a dynamic regulator with an internal model to drive agents towards the moving target merely by position information feedback, and a repulsive force between each pair of adjacent agents. Significantly, sufficient conditions are derived to guarantee the asymptotic stability of the closed-loop systems governed by the proposed fencing controller. Rigorous analysis is provided to eliminate the strong nonlinear couplings induced by the label-free property. Finally, the effectiveness of the controller is substantiated by numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Single-Cell Clustering Algorithm Based on Structure Perturbation Non-Negative Matrix Factorization

A Single-Cell Clustering Algorithm Based on Structure Pertur...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Hanjing Wang, Meineng Zhang, Luping Huang, Yu-An Li, Yangyuan Huang, Yabing Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Hubei Wuhan430074 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Yichun University School of Mathematics and Computer Science Yichun336000 China East China University of Technology School of Information Engineering Nanchang330013 China Northwestern Polytechnical University School of Computer Science Xi'an710129 China Renmin Hospital Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350386226

The advent of single-cell RNA sequencing (scRNA-seq) has facilitated the acquisition of high-resolution data regarding cell heterogeneity across various tissues. A fundamental and critical step in the analysis of scRNA-seq data is cell type identification. An appropriate graph construction strategy can reflect the topological structure between cells and allows for detailed exploration of the relationships between cells and genes. Given the sparsity of scRNA-seq data and the pronounced noise generated by shallow sequencing, choosing an appropriate graph construction strategy has become a significant challenge. In this paper, we propose a single-cell clustering method, named Sc-PNNMF, based on structural perturbation of nonnegative matrix factorization. Sc-PNNMF employs a structural perturbation algorithm to optimize the gene expression matrix. The optimized matrix guides the matrix factorization process, effectively overcoming the impact of data sparsity and significant noise in gene expression data on the graph construction strategy. We compared the clustering abilities of Sc-PNNMF with five other methods on ten real datasets. © 2024 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs

arXiv

引用

arXiv 2024年

作者： Li, Siyang Wang, Ziwei Luo, Hanbin Ding, Lieyun 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 Shenzhen China Henan Key Laboratory of Brain Science and Brain Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University China School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China

Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) enables direct communication between the human brain and a computer. Due to individual differences and non-stationarity of EEG signals, such BCIs usually require a subject-specific calibration session before each use, which is time-consuming and user-unfriendly. Transfer learning (TL) has been proposed to shorten or eliminate this calibration, but existing TL approaches mainly consider offline settings, where all unlabeled EEG trials from the new user are available. Methods: This paper proposes Test-Time Information Maximization Ensemble (T-TIME) to accommodate the most challenging online TL scenario, where unlabeled EEG data from the new user arrive in a stream, and immediate classification is performed. T-TIME initializes multiple classifiers from the aligned source data. When an unlabeled test EEG trial arrives, T-TIME first predicts its labels using ensemble learning, and then updates each classifier by conditional entropy minimization and adaptive marginal distribution regularization. Our code is publicized. Results: Extensive experiments on three public motor imagery based BCI datasets demonstrated that T-TIME outperformed about 20 classical and state-of-the-art TL approaches. Significance: To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible. © 2024, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Dense Pixel-to-Pixel Harmonization via Continuous image Representation

arXiv

引用

arXiv 2023年

作者： Chen, Jianqi Zhang, Yilan Zou, Zhengxia Chen, keyan Shi, Zhenwei Image Processing Center School of Astronautics Beihang University Beijing100191 China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing100191 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Department of Guidance Navigation and Control School of Astronautics Beihang University Beijing100191 China

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing. However, due to the high memory costs, existing dense pixel-to-pixel harmonization methods are mainly focusing on processing low-resolution (LR) images. Some recent works resort to combining with color-to-color transformations but are either limited to certain resolutions or heavily depend on hand-crafted image filters. In this work, we explore leveraging the implicit neural representation (INR) and propose a novel image Harmonization method based on Implicit neural Networks (HINet), which to the best of our knowledge, is the first dense pixel-to-pixel method applicable to HR images without any handcrafted filter design. Inspired by the Retinex theory, we decouple the MLPs into two parts to respectively capture the content and environment of composite images. A Low-Resolution image Prior (LRIP) network is designed to alleviate the Boundary Inconsistency problem, and we also propose new designs for the training and inference process. Extensive experiments have demonstrated the effectiveness of our method compared with state-of-the-art methods. Furthermore, some interesting and practical applications of the proposed method are explored. Our code is available at https://***/WindVChen/INR-Harmonization. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：