检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Jiankang Zhang, Tong Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China

Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (‘anchors’) from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluations on multiple OOD detection benchmarks demonstrate that rich textual representation of ID knowledge and fake OOD knowledge can well help train a visual encoder for OOD detection. With the learning framework, new state-of-the-art performance was achieved on all the benchmarks. The code is available at https://***/Cverchen/TagFog. Copyright © 2024, The Authors. All rights reserved.

关键词： Jigs

来源：评论

学校读者我要写书评

暂无评论

TexCIL: Text-Guided Continual Learning of Disease with Vision-Language Model

TexCIL: Text-Guided Continual Learning of Disease with Visio...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Wentao Zhang Defeng Zhao Wei-Shi Zheng Ruixuan Wang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Current intelligent diagnostic systems often catastrophically forget old knowledge when learning new diseases only from the training dataset of the new diseases. Inspired by human learning of visual classes with the effective help of language, we propose a continual learning framework based on a pre-trained visual-language model (VLM) without storing any image of previously learned diseases. In this framework, textual prior knowledge of each new disease can be obtained by utilizing the frozen VLM’s text encoder, and then used to guide the visual learning of the new disease. This framework innovatively utilizes the textual prior knowledge of all previously learned diseases as out-of-distribution (OOD) information to help differentiate currently being-learned diseases from others. Extensive empirical evaluations on both medical and natural image datasets confirm the superiority of the proposed method over existing state-of-the-art methods in continual learning of new visual classes. The source code is available at https://***/OpenMedIA/TexCIL.

关键词： Continuing education Training Visualization Source coding Biological system modeling Benchmark testing Bioinformatics Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Effect of Camera Position on Knee Angle Extracted by Single RGB Camera Markerless Method of Human Posture

Effect of Camera Position on Knee Angle Extracted by Single ...

引用

2023 IEEE International Conference on Real-Time computing and Robotics, RCAR 2023

作者： Hu, Rui Diao, Yanan Sheng, Juyi Sun, Yue Ning, Yunkun Liu, GenYuan Wang, Yingchi Li, Guanglin Zhao, Guoru Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Research Center for Neural Engineering Shenzhen Institutes of Advanced Technology China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen China

ISBN: (纸本)9798350327182

Medical rehabilitation robots have shown strong potential for rehabilitation assessment and monitoring of the elderly. Accurate estimation of human posture based on video analysis can help the clinical application of medical rehabilitation robots. However, the current human pose estimation still needs to improve its accuracy;it is missing 3D posture information and has an unclear occlusion effect on accuracy. This paper proposes a markerless human pose measurement method based on a monocular RGB camera to find the knee joint angle using a 2D and 3D pose estimator. Eleven young people were recruited to participate in the experiments to study the effects of different camera positions on the joint angle extraction results. The results showed a camera angle of 45° was more effective in measuring sitting posture, with a standard deviation of 5.97 for the left leg. A camera angle of 90° was more effective in measuring gait, with a standard deviation of 9.34 for the left leg. In summary, the proposed method can fully use 3D posture information and consider the influence of camera angle on accuracy to improve posture estimation accuracy. The execution of this study is beneficial to promote medical rehabilitation robots to clinical applications. © 2023 IEEE.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Improvement and optimization of consensus algorithm based on PBFT 4

Improvement and optimization of consensus algorithm based on...

引用

4th International Conference on Communications, Information System and Computer Engineering, CISCE 2022

作者： Zhao, Liang Li, Bin Zhou, Qinglei Chen, Xiaojie Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (数字)9781665498487

ISBN: (纸本)9781665498487

This paper proposes an improved consensus algorithm based on PBFT(EBCR-PBFT). Firstly, The Modified Random Select(MRS) function is used to perform preliminary screening of network nodes, so as to solve the problem of multiple and redundant network nodes. Secondly, based on the idea of clustering, logical stratification of blockchain network nodes can reduce communication times and improve network efficiency. Thirdly, the core module of MRS is optimized by FPGA to further improve the efficiency of the algorithm. At the same time, the improved dynamic reputation evaluation model is introduced to evaluate and feedback the node behavior in time to ensure the smooth operation of the system. Experiments show that the proposed and optimized consensus algorithm can effectively improve the consensus efficiency, timely punish malicious nodes, increase the reliability of nodes, communication overhead, throughput, delay and other high performance, has a certain application value. © 2022 IEEE.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

TightLLM: Maximizing Throughput for LLM Inference via Adaptive Offloading Policy

引用

IEEE Transactions on Computers 2025年

作者： Hu, Yitao Liu, Xiulong Yang, Guotao Li, Linxuan Zeng, Kai Zhao, Zhixin Chen, Sheng Zhao, Laiping Li, Wenxin Li, Keqiu Tianjin University Tianjin Key Laboratory of Advanced Networking Tianjin300350 China Tianjin University Department of Intelligence and Computing Tianjin300350 China

Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks, largely due to their substantial model size. However, this also results in significant GPU memory demands during inference. To address these challenges on hardware with limited GPU memory, existing approaches employ offloading techniques that offload unused tensors to CPU memory, thereby reducing GPU memory usage. Since offloading involves data transfer between GPU and CPU, it introduces transfer overhead. To mitigate this, prior works typically overlap data transfer with GPU computation using a fixed pipelining strategy applied uniformly across all inference iterations, referred to as static offloading. However, static offloading policies fail to maximize inference throughput because they cannot adapt to the dynamically changing transfer overhead during the inference process, leading to increasing GPU idleness and reduced inference *** propose that offloading policies should be adaptive to the varying transfer overhead across inference iterations to maximize inference throughput. To this end, we design and implement an adaptive offloading-based inference system called TightLLM with two key innovations. First, its key-value (KV) distributor employs a trade-compute-for-transfer strategy to address growing transfer overhead by dynamically recomputing portions of the KV cache, effectively overlapping data transfer with computation and minimizing GPU idleness. Second, TightLLM’s weight loader slices model weights and distributes the loading process across multiple batches, amortizing the excessive weight loading overhead and significantly improving throughput. Evaluation across various combinations of GPU hardware and LLM models shows that TightLLM achieves 1.3 to 23 times higher throughput during the decoding phase and 1.2 to 22 times higher throughput in the prefill phase compared to state-of-the-art offloading systems. Due to the higher throughput in prefill

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Debiasing Recommenders Through Personalized Popularity-Aware Margins

Debiasing Recommenders Through Personalized Popularity-Aware...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ruiguo Yu Yue Chen Mankun Zhao Jian Yu Tianyi Xu Mei Yu Xuewei Li College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China

Recommender systems based on Matrix Factorization are widely used. However, they can easily suffer from the problem of overrecommendation of popular items, i.e., popularity bias. To mitigate popularity bias, current methods often uniformly model interactions' popularity bias degree considering user activity and interacted item's popularity, and then force the recommenders to focus more on less biased interactions. However, users' popularity preference for candidate items also plays an important role in estimating popularity bias, which is ignored by current methods. Therefore, their uniform modeling of bias degree results in sub-optimal debiasing performance. To address this issue, our core idea is to estimate personalized bias degrees to perform user-specific debiasing. We first derive a predefined bias degree obtained by items' popularity, then scale it considering users' candidate items' popularity. Extensive experiments conducted on two classic MF-based recommenders and three real-world datasets demonstrate that our approach outperforms state-of-the-art methods for popularity debiasing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

arXiv

引用

arXiv 2024年

作者： Xu, Angchi Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer pseudo segmentation for training by serial alignment between all frames and the transcript, which is time-consuming and hard to be parallelized while training. In this work, we aim to escape from this inefficient alignment with massive but redundant frames, and instead to directly localize a few action transitions for pseudo segmentation generation, where a transition refers to the change from an action segment to its next adjacent one in the transcript. As the true transitions are submerged in noisy boundaries due to intra-segment visual variation, we propose a novel Action-Transition-Aware Boundary Alignment (ATBA) framework to efficiently and effectively filter out noisy boundaries and detect transitions. In addition, to boost the semantic learning in the case that noise is inevitably present in the pseudo segmentation, we also introduce video-level losses to utilize the trusted video-level supervision. Extensive experiments show the effectiveness of our approach on both performance and training speed. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Confidence-guided Source Label Refinement and Class-aware Pseudo-Label Thresholding for Domain-Adaptive Semantic Segmentation

Confidence-guided Source Label Refinement and Class-aware Ps...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hongwei Chu Meng Shen Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Domain-Adaptive Semantic Segmentation (DASS) aims to transfer a segmentation model trained on a labeled source domain to an unlabeled target domain. Most existing methods overlook the errors in the source labels and directly utilize the erroneous source labels for training. This may result in wrong source domain knowledge being wrongly transferred to the target domain, which leads to similar classes cannot be separated well in the target domain. To this end, we propose a novel Confidence-guided Online REfinement (CORE) method, which introduces a refinement network trained on the target data to rectify erroneous source labels online. This can effectively avoid transferring erroneous knowledge from the source domain to the target domain. On the other hand, using the same threshold for all classes in the target domain may result in a severe class imbalance in self-training. Therefore, we propose Class-aware Adaptive Thresholding (CAT) to calculate different thresholds for different target classes, which adaptively filter target pixels with high confidence for better adaptation. Our proposed CORE-CAT method can be easily integrated with existing methods and achieves superior performance across various domain-adaptive semantic segmentation benchmarks.

关键词： Training Adaptation models Semantic segmentation Neural networks Adaptive filters Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Single-View Scene Point Cloud Human Grasp Generation

Single-View Scene Point Cloud Human Grasp Generation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yan-Kang Wang Chengyi Xing Yi-Lin Wei Xiao-Ming Wu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Stanford University Stanford CA Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this work, we explore a novel task of generating human grasps based on single-view scene point clouds, which more accurately mirrors the typical real-world situation of observing objects from a single viewpoint. Due to the incompleteness of object point clouds and the presence of numerous scene points, the generated hand is prone to penetrating into the invisible parts of the object and the model is easily affected by scene points. Thus, we introduce S2HGrasp, a framework composed of two key modules: the Global Perception module that globally perceives partial object point clouds, and the DiffuGrasp module designed to generate high-quality human grasps based on complex inputs that include scene points. Additionally, we introduce S2HGD dataset, which comprises approximately 99,000 single-object single-view scene point clouds of 1,668 unique objects, each annotated with one human grasp. Our extensive experiments demonstrate that S2HGrasp can not only generate natural human grasps regardless of scene points, but also effectively prevent penetration between the hand and invisible parts of the object. Moreover, our model showcases strong generalization capability when applied to unseen objects. Our code and dataset are available at https://***/iSEE-laboratory/S2HGrasp.

关键词： Point cloud compression Computer vision Codes Computational modeling Pattern recognition Mirrors Task analysis

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：