检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Wenxuan Huang Yunhang Shen Jiao Xie Baochang Zhang Gaoqi He Ke Li Xing Sun Shaohui Lin School of Computer Science and Technology East China Normal University Shanghai China Tencent Youtu Lab China Xiamen University China Beihang University China Key Laboratory of Advanced Theory and Application in Statistics and Data Science - MOE China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyperparameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an “initialization-expansion-merging” pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyperparameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3× faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://***/Osilly/TokenExpansion.

关键词： Training computer vision Accuracy Costs Codes Pipelines computer architecture

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Gland Segmentation with Class Semantic Consistency and Purified Labels Filtration 39

Weakly Supervised Gland Segmentation with Class Semantic Con...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Feng, Siyang Wang, Huadeng Han, Chu Liu, Zhenbing Zhang, Hualong Lan, Rushi Pan, Xipeng School of Computer Science and Information Security Guilin University of Electronic Technology Guilin 541004 China Guangdong Provincial Key Laboratory of Artificial Intelligence Medical Image Analysis and Application Guangzhou 510080 China International Joint Research Laboratory of Spatio-temporal Information and Intelligent Location Services Guilin University of Electronic Technology Guilin 541004 China

ISBN: (纸本)157735897X

Image-level weakly supervised semantic segmentation (WSSS) reduces the dependence on high-quality data annotation, which plays a crucial role in computational pathology. Benefit from the ability to localize the objects with only binary labels, Class Activation Map (CAM) is a widely used method to initial pseudo masks. However, due to the low contrast among different tissues in histopathological images, most existing CAM-based methods perform poorly in gland segmentation. We retrospect this process and find that class consistency and semantic consistency can guide the network to effectively distinguish confusing pixels and generate fine-grained pseudo masks. Specifically, for class consistency, we propose Consistency Correlation Attention (CCA) to encourage the network to focus on the contribution of class features to semantic dependencies. For semantic consistency, we propose Multi-scale Pyramid Fusion Pooling (MPFP) to aggregate coarse-to-fine global semantic information from CAMs at multiple spatial resolutions, thus identifying class localization. Additionally, we introduce a Purified Labels Filtration (PLF) strategy during the segmentation phase to mitigate the noisy supervision signal and improve the segmentation quality of the model. Extensive experiments show that the our method achieves new state-of-the-art results on three publicly available gland datasets. Furthermore, our method demonstrates impressive domain adaptation capability, achieving satisfactory results with only a small portion of samples when faced with unseen domain data. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A General and Efficient Training for Transformer via Token Expansion

arXiv

引用

arXiv 2024年

作者： Huang, Wenxuan Shen, Yunhang Xie, Jiao Zhang, Baochang He, Gaoqi Li, Ke Sun, Xing Lin, Shaohui School of Computer Science and Technology East China Normal University Shanghai China Tencent Youtu Lab China Xiamen University China Beihang University China Key Laboratory of Advanced Theory and Application in Statistics and Data Science - MOE China

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyper-parameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an "initialization-expansion-merging" pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyper-parameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3× faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://***/Osilly/TokenExpansion. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

HiCoCS: High Concurrency Cross-Sharding on Permissioned Blockchains

引用

IEEE Transactions on computers 2025年第07期74卷 2168-2182页

作者： Yang, Lingxiao Dong, Xuewen Wan, Zhiguo Lu, Di Zhang, Yushu Shen, Yulong Xidian University School of Computer Science and Technology China Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China Zhejiang Lab Zhejiang Hangzhou311121 China Shaanxi Key Laboratory of Network and System Security Xi’an710071 China Jiangxi University of Finance and Economics School of Computing Nanchang330013 China Jiangxi University of Finance and Economics Nanchang330013 China

As the foundation of the Web3 trust system, blockchain technology faces increasing demands for scalability. Sharding emerges as a promising solution, but it struggles to handle highly concurrent cross-shard transactions (CSTxs), primarily due to simultaneous ledger operations on the same account. Hyperledger Fabric, a permissioned blockchain, employs multi-version concurrency control for parallel processing. Existing solutions use channels and intermediaries to achieve cross-sharding in Hyperledger Fabric. However, the conflict problem caused by highly concurrent CSTxs has not been adequately resolved. To fill this gap, we propose HiCoCS, a high concurrency cross-shard scheme for permissioned blockchains. HiCoCS creates a unique virtual sub-broker for each CSTx by introducing a composite key structure, enabling conflict-free concurrent transaction processing while reducing resource overhead. The challenge lies in managing large numbers of composite keys and mitigating intermediary privacy risks. HiCoCS utilizes virtual sub-brokers to receive and process CSTxs concurrently while maintaining a transaction pool. Batch processing is employed to merge multiple CSTxs in the pool, improving efficiency. We explore composite key reuse to reduce the number of virtual sub-brokers and lower system overhead. Privacy preservation is enhanced using homomorphic encryption. Evaluations show that HiCoCS improves cross-shard transaction throughput by 3.5-20.2 times compared to the baselines. © 1968-2012 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Rore: robust and efficient antioxidant protein classification via a novel dimensionality reduction strategy based on learning of fewer features

引用

Genomics and Informatics 2024年第1期22卷 1-10页

作者： Meng, Chaolu Hou, Yongqi Zou, Quan Shi, Lei Su, Xi Ju, Ying College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry Hohhot China School of Computer Science Inner Mongolia University Hohhot China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China Department of Spine Surgery Changzheng Hospital Naval Medical University Huangpu District No. 415 Fengyang Road Shanghai China Foshan Women and Children Hospital Foshan China School of Informatics Xiamen University Xiamen China

In protein identification, researchers increasingly aim to achieve efficient classification using fewer features. While many feature selection methods effectively reduce the number of model features, they often cause information loss caused by merely selecting or discarding features, which limits classifier performance. To address this issue, we present Rore, an algorithm based on a feature-dimensionality reduction strategy. By mapping the original features to a latent space, Rore retains all relevant feature information while using fewer representations of the latent features. This approach significantly preserves the original information and overcomes the information loss problem associated with previous feature selection. Through extensive experimental validation and analysis, Rore demonstrated excellent performance on an antioxidant protein dataset, achieving an accuracy of 95.88% and MCC of 91.78%, using vectors including only 15 features. The Rore algorithm is available online at http://112.124.26.17:8021/Rore. © The Author(s) 2024.

关键词： Dimensionality reduction Protein classifier Protein sequence Robust feature

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-view Clustering Based on Joint Concept Decomposition and Anchor Graph Learning 11th

Incomplete Multi-view Clustering Based on Joint Concept Dec...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Li, Zhuowen Chen, Hongmei Xiang, Biao Yuan, Zhong Luo, Chuan Li, Tianrui School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu 611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 China College of Computer Science Sichuan University Chengdu 610065 China

ISBN: (纸本)9783031927430

The main objective of incomplete multi-view clustering is to effectively utilize the existing view information to fill in the missing data and to mine the complementary information and potential associations between multiple views to effectively group samples. The existing primary means for recovering missing information are classified into two parts: one uses matrix decomposition or low-rank constraints to fill in the missing views, and the other constructs multiple graph structures and uses graph regularization to recover the corresponding missing parts. However, the two methods are relatively independent and are not used jointly to improve the model performance. This paper proposes an incomplete multi-view clustering method with complete clustering metrics and complete anchor graphs (CFAG). Specifically, each view’s missing samples are recovered by a matrix of consistent clustering metrics and represented by an anchor graph. The recovered complete data performs anchor graph construction and anchor learning and utilizes the orthogonal variation principle to learn the consistency structure of multiple anchor graphs to mine the complementary information among multiple views. The clustering metrics are obtained based on the consistency structure, and the consistency of the clustering metrics is also considered to obtain the final clustering results. The effectiveness of the proposed method is verified on multiple datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anchor graph Incomplete multi-view clustering Missing views recovery

来源：评论

学校读者我要写书评

暂无评论

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded ...

引用

2022 International Conference on Radar Systems, RADAR 2022

作者： Wang, Muhan Zhang, Zhe Wang, Yue Gao, Silin Qiu, Xiaolan Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Electrical and Computer Engineering Department George Mason University FairfaxVA22030 United States

ISBN: (纸本)9781839537776

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Index Modulated OFDM Spread Spectrum for Underwater Acoustic Integrated Sensing and Communication Networks

Adaptive Index Modulated OFDM Spread Spectrum for Underwater...

引用

2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023

作者： Wang, Junfeng Cui, Yue Zhou, Mingzhang Sun, Haixin Liu, Lanjun Zhang, Ailing School of Integrated Circuit Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of Southeast Coast Marine Information Intelligent Perception and Application MNR China College of Computer and Information Engineering Tianjin Normal University Tianjin300387 China School of Information Science and Engineering Xiamen University Xiamen361005 China College of Engineering Ocean University of China Qingdao266100 China

ISBN: (纸本)9798350316728

It is predicted that underwater acoustic integrated sensing and communication networks (UAISACNs) would be one of the main enablers for supporting a variety of emerging applications due to benefits of communication-Assisted sensing, sensing-Assisted communication and their integration. Mean-while, link adaptation and index modulated orthogonal frequency division multiplexing spread spectrum (IM-OFDM-SS) are a kind of powerful transmission technique for underwater acoustic communications networks, which can exploit the time-varying behavior of underwater communication channels to transmit much higher speeds. Thus, this paper aims to propose the adaptive IM-OFDM-SS for the UAISACNs, where the adaptive technique is integrated with the IM-OFDM-SS. The presented scheme is capable of adaptive transmitting the downlink information to the communication node in the UAISACNs by employing the estimating sensing parameters of its echo, which can reduce large amount of the signaling overhead and the long latency resulted from the conventional feedback-based protocol. Our suggested framework can choose the best possible transmission mode to maximize the achievable throughput, which can be verified through computer simulations, where we show the benefits of our proposed adaptive transmission scheme. © 2023 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Collaborative List-and-Pairwise Filtering from Implicit Feedback : Extended Abstract

Collaborative List-and-Pairwise Filtering from Implicit Feed...

引用

International Conference on Data Engineering

作者： Runlong Yu Qi Liu Yuyang Ye Mingyue Cheng Enhong Chen Jianhui Ma Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Hefei China Management Science and Information Systems Rutgers Business School Rutgers University Newark USA

Collaborative filtering (CF) from implicit datasets has attracted much attention in recent years. The current mainstream pairwise methods optimize the Area Under the Curve (AUC) and are empirically proven to be helpful to exploit implicit feedback, but lead to not addressing the rank-biased scenarios where positive items are supposed to be placed on the top-k positions. Although there exist listwise methods, they have low efficiency and are not particularly adequate for general implicit feedback situations. To that end, in this paper, we propose a new framework, namely Collaborative List-and-Pairwise Filtering (CLAPF), which aims to introduce pairwise thinking into listwise methods. Specifically, we first smooth a well-known rank-biased measure called Mean Average Precision (MAP) as a low-bound version to make it can be optimized. After that, we combined the objective functions of optimizing the MAP with pairwise comparisons. The CLAPF framework is a new hybrid model that provides the idea of utilizing a listwise measure in a pairwise way on implicit feedback.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Contrastive Patch Comparison Transformer for Weakly Supervised Semantic Segmentation

Contrastive Patch Comparison Transformer for Weakly Supervis...

引用

IEEE International Conference on Smart Internet of Things (SmartIoT)

作者： Wentian Cai Weixian Yang Jing Lin Ying Gao School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China

ISBN: (数字)9798350366440

ISBN: (纸本)9798350366457

Weakly supervised semantic segmentation (WSSS) focuses on utilizing image-level labels to classify all pixels into object classes or background class. Class Activation Mapping (CAM) highlights the most discriminative region of the target object, but fails to discover minor details in whole image. The gap between classification task and segmentation task causes a reduction in the accuracy. In this paper, we propose a simple-yet-efficient WSSS framework based on Transformer backbone. We introduce a patch-wise contrastive learning module to discover potential patch embedding information. Additionally, we introduced a multi-scale supervision to constrain the network to focus on target objects while learning patch-wise contrasty. Experimental results validate that our framework yields good performance on VOC2012 without using any salient maps.

关键词： Accuracy Semantic segmentation Semantics Contrastive learning Transformers Internet of Things

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：