检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Haobo Wang Mingxuan Xia Yixuan Li Yuren Mao Lei Feng Gang Chen Junbo Zhao Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University School of Software Technology Zhejiang University Department of Computer Sciences University of Wisconsin-Madison College of Computer Science Chongqing University and Center for Advanced Intelligence Project RIKEN

ISBN: (纸本)9781713871088

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods have been proposed in this domain, they normally assume a class-balanced scenario that may not hold in many real-world applications. Empirically, we observe degenerated performance of the prior methods when facing the combinatorial challenge from the long-tailed distribution and partial-labeling. In this work, we first identify the major reasons that the prior work failed. We subsequently propose SoLar, a novel Optimal Transport-based framework that allows to refine the disambiguated labels towards matching the marginal class prior distribution. SoLar additionally incorporates a new and systematic mechanism for estimating the long-tailed class prior distribution under the PLL setup. Through extensive experiments, SoLar exhibits substantially superior results on standardized benchmarks compared to the previous state-of-the-art PLL methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long-Tailed Multi-label Classification with Noisy label of Thoracic Diseases from Chest X-Ray

Long-Tailed Multi-Label Classification with Noisy Label of T...

引用

IEEE International Symposium on Biomedical Imaging

作者： Haoran Lai Qingsong Yao Zhiyang He Xiaodong Tao S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei P.R. China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Medical Business Department iFlytek Co. Ltd Hefei China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Chest X-rays (CXR) often reveal rare diseases, demanding precise diagnosis. However, current computer-aided diagnosis (CAD) methods focus on common diseases, leading to inadequate detection of rare conditions due to the absence of comprehensive datasets. To overcome this, we present a novel benchmark for long-tailed multi-label classification in CXRs, encapsulating both common and rare thoracic diseases. Our approach includes developing the "LTML-MIMIC-CXR" dataset, an augmentation of MIMIC-CXR with 26 additional rare diseases. We propose a baseline method for this classification challenge, integrating adaptive negative regularization to address negative logits' over-suppression in tail classes, and a large loss reconsideration strategy for correcting noisy labels from automated annotations. Our evaluation on LTML- MIMIC-CXR demonstrates significant advancements in rare disease detection. This work establishes a foundation for robust CAD methods, achieving a balance in identifying a spectrum of thoracic diseases in CXRs. Access to our code and dataset is provided at: https://***/laihaoran/LTML-MIMIC-CXR.

关键词： design automation Annotations MIMICs Pipelines Tail Computer aided diagnosis Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Hand Pose Estimation Using Convolutional Neural Networks and Support Vector Regression 12th

Hand Pose Estimation Using Convolutional Neural Networks and...

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Dong, Yufeng Lu, Jian Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China

ISBN: (纸本)9783030237110

In order to improve the accuracy of hand pose estimation from a depth image, a method based on convolutional neural network (CNN) is proposed in this paper. First of all, we modify the structure of traditional CNN to recognize the 3D joint locations from a depth image. By appending some shortcuts between layers, the proposed network increases the correlation between the front and back layers. This structure can avoid the information loss caused by the simple layer-by-layer transmission, and can improve the estimation accuracy effectively. Afterwards, the estimated joint locations continue to be inputted into a support vector regression (SVR) phase. The use of SVR can introduce the constraint of local joint information, which can get rid of those abnormal estimations further. Extensive experiments show that our method enables significant performance improvement over the-state-of-arts in the accuracy of hand pose estimation. © 2019, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Low SAR, Small size, High gain, Circularly polarized Antenna for Wearable Application 2

A Low SAR, Small size, High gain, Circularly polarized Anten...

引用

2020 2nd International Conference on Artificial Intelligence Technologies and Application, ICAITA 2020

作者： Wang, Chao Zhang, Liang Cheng, Yi Li, XueMei Wu, Xianliang Key Lab of Ministry of Education of Intelligent Computing and Signal Processing Anhui University Hefei Anhui230601 China AnHui Province Key Laboratory of Simulation and Design for Electronic Information System Hefei Normal University Hefei Anhui230601 China

A planar, small size, high gain, low specific absorption rate (SAR) and circularly-polarized (CP) wearable antenna is proposed in this paper. The antenna is fabricated on a substrate with a dielectric constant of 3.5 with a thickness of 0.5 mm and sized at 42×42 mm only. Both the simulation results show that the overlap bandwidth of impedance and axial ratio of the proposed antenna is 13.7% (5.15-5.91 GHz). To isolate the antenna against the influence of the human body, a artificial magnetic conductor (AMC) plane is added on the reverse side of the radiator. The AMC structure effectively isolates the human body from the radiation of the antenna and reduces the specific absorption rate (SAR) of it by more than 96.1% at 5.5 GHz, which improves the antenna gain and the peak gain reaches 5.09 dBi at 5.5 GHz. The wearable performance of the antenna was analyzed, and it is observed that it can sustain good performance even under human body loading. Beside, the antenna has a small size, which makes it ideal for wearable applications. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Wearable antennas

来源：评论

学校读者我要写书评

暂无评论

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaoqing Nie, Qiushi Xiao, Zunjie Zhao, Jilu Wu, Xiao Guo, Pengxin Li, Runzhi Liu, Jin Wei, Yanjie Pan, Yi Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Actuarial Science The University of Hong Kong 999077 Hong Kong Cooperative Innovation Center of Internet Healthcare Zhengzhou University Zhengzhou450001 China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830046 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs. © 2024, 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

CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification

CARZero: Cross-Attention Alignment for Radiology Zero-Shot C...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haoran Lai Qingsong Yao Zihang Jiang Rongsheng Wang Zhiyang He Xiaodong Tao S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui P.R.China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu P.R.China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Medical Business Department iFlytek Co.Ltd Hefei China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The advancement of Zero-Shot Learning in the medi-cal domain has been driven forward by using pretrained models on large-scale image-text pairs, focusing on image-text alignment. However, existing methods primarily rely on cosine similarity for alignment, which may not fully capture the complex relationship between medical images and reports. To address this gap, we introduce a novel approach called Cross-Attention Alignment for Radiology Zero-Shot Classification (CARZero). Our approach innovatively leverages cross-attention mechanisms to process image and report features, creating a Similarity Representation that more accurately reflects the intricate relationships in medical semantics. This representation is then linearly projected to form an image-text similarity matrix for cross-modality alignment. Additionally, recognizing the pivotal role of prompt selection in zero-shot learning, CARZero in-corporates a Large Language Model-based prompt alignment strategy. This strategy standardizes diverse diagnostic expressions into a unified format for both training and inference phases, overcoming the challenges of manual prompt design. Our approach is simple yet effective, demonstrating state-of-the-art performance in zero-shot classification on five official chest radiograph diagnostic test sets, including remarkable results on datasets with long-tail distributions of rare diseases. This achievement is attributed to our new image-text alignment strategy, which effectively addresses the complex relationship between medical images and reports. Code and models are available at https://***/laihaoran/CARZero.

关键词： Training Zero-shot learning Semantics Focusing Manuals Radiology Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Second-Order Pooling Convolutional Networks

Attention-Guided Second-Order Pooling Convolutional Networks

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Shannan Chen Qiule Sun Cunhua Li Jianxin Zhang Qiang Zhang Key Lab of Advanced Design and Intelligent Computing Dalian University China Faculty of Electronic Information and Electrical Engineering Dalian University of Technology China School of Computer Engineering Jiangsu Ocean University China School of Computer Science and Engineering Dalian Minzu University China

Recently, channel attention-guided convolutional networks (ConvNets) have shown great advance on visual recognition tasks. However, they mainly exploit coarse first-order statistics to characterize holistic image and rarely focus on long-range feature dependencies, which limits the representation power in a certain. To handle above limitations, this paper proposes a novel attention-guided second-order pooling convolutional network (ASP-Net). ASP-Net introduces bilinear pooling that captures pairwise feature interactions to model second-order statistics. Meanwhile, it explicitly collects long-range dependencies via non-local operations, thus providing a global view in lower layers. Then, the second-order statistics and non-local context features are fused to obtain the enhanced representation for predicting channel-wise attention map and scaling convolution features. Experiment results on three commonly used datasets illuminate that ASP-Net outperforms its counterparts and achieves competitive performance.

关键词： Convolutional codes Visualization Convolution Conferences Network architecture Acoustics Task analysis

来源：评论

学校读者我要写书评

暂无评论

Liquid Metal Manifold Microchannel Heat Sink for Ultra-High Heat Flux Cooling

SSRN

引用

SSRN 2024年

作者： Zhang, Mingkuan Gao, Qi Zhao, Zhiyuan Guo, Luna Li, Xuan Zhang, Chao Zhang, Xudong Rao, Wei Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control School of Mechanical Engineering Tianjin University of Technology Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology China School of mechanical engineering Tianjin University of Commerce Tianjin300134 China Institute of Refrigeration and Cryogenics Shanghai Jiao Tong University Shanghai200240 China Key Laboratory for Thermal Science and Power Engineering of Ministry of Education Department of Engineering Mechanics Tsinghua University Beijing Beijing100084 China CAS Key Laboratory of Cryogenics Technical Institute of Physics and Chemistry Chinese Academy of Sciences China Beijing Key Lab of CryoBiomedical Engineering and Key Lab of Cryogenics Beijing100190 China

The reduction in transistor dimensions and advancements in chip integration have led to a dramatic increase in the heat flux of chip. advanced heat dissipation technology has become the pivotal in ensuring the normal operation of chips and fully utilizing chip performance. Room temperature liquid metal convection cooling technology has demonstrated its efficacy as a viable approach for addressing high heat flux heat dissipation. However, the smaller specific heat capacity of liquid metal leads to a large temperature rise, imposing a constraint on the progression of liquid metal cooling technology. To overcome this drawback, this paper proposed a liquid metal manifold channel structure designed to convert the continuous long-range flow into a segmented short-range flow. The good matching between liquid metal and manifold structures is adequately demonstrated through a comparison with alternative coolant and channel structure. The simulation results demonstrate the effectiveness of liquid metal manifold channel cooling in dealing with a heat flux of 1000 W/cm², ensuring that the maximum temperature of the chip remains below 351.7 K. Moreover, the convective heat transfer coefficient even reaches 106 W/(m2·K), which is ten times larger than that of water conventional microchannel heat sink. The orthogonal experiments were conducted to analyze how the structural parameters affect the dissipation performance, including the height of the microchannel, ratio of manifold length to fin length, length of fin in manifold, width of channel, and ratio of fin with to channel width. It concluded that the height of the microchannel has been identified as the most critical factor. This manifold structure mitigates the inherent limitation of the lower specific heat capacity of liquid metal, paving the way for effective thermal management of electronic devices subjected to ultra-high heat flux. © 2024, The Authors. All rights reserved.

关键词： Heat flux

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SoLar: Sinkhorn label Refinery for Imbalanced Partial-label Learning

arXiv

引用

arXiv 2022年

作者： Wang, Haobo Xia, Mingxuan Li, Yixuan Mao, Yuren Feng, Lei Chen, Gang Zhao, Junbo Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University China School of Software Technology Zhejiang University China Department of Computer Sciences University of Wisconsin-Madison United States College of Computer Science Chongqing University China Center for Advanced Intelligence Project RIKEN Japan

关键词： Machine learning

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：