检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jiaxin Chen Yanxu Hu Meng Shen Andy J. Ma School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Unsupervised Few-shot Learning (UFSL) is a practical approach to adapting knowledge learned from unlabeled data of base classes to novel classes with limited labeled data. Nevertheless, most existing UFSL methods may not learn generalizable features in latter training epochs due to the simplicity of meta-learning tasks constructed by data augmentation. To address this issue, we propose two novel components, namely Dual Episodic Sampling (DES) and Momentum Consistency Regularization (MCR) for UFSL. In the DES, two types of sampling strategies are used to construct harder training tasks with multiple augmentations to generate each pseudo-class of increased diversity. The MCR constrains the consistency of the backbone encoder with its momentum counterpart to learn better generalized features for novel classes. Experimental results on four datasets verify the superiority of our method for unsupervised few-shot image classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DualGCN-MIL: Whole Slide Image Classification Based on Double Relationship Graph Learning

DualGCN-MIL: Whole Slide Image Classification Based on Doubl...

引用

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

作者： Mei Yu Hexin Wang Xuzhou Fu Jie Gao Zhiqiang Liu Xuewei Li School of Feature Technology Tianjin University Tianjin China 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

The resolution of a whole slide image (WSI) is too large to process directly, but WSI can be segmented into patches and be classified through multiple instance learning (MIL). Some patches have either close distances or similar pathological morphology, indicating that there are at least two types of relationships between patches. However, the existing MIL methods often deal with instance relationships simplistically. To solve this problem, we propose a new model named DualGCN-MIL. It analyzes the two types of relationships in WSI by constructing two different graphs in high-dimensional feature space and physical coordinate space and uses graph convolutional networks with unshared parameters for learning. Various experiments conducted on the Camelyon dataset have shown that compared to state-of-the-art methods, we can achieve better performance in multiple indicators, with accuracy of 88.89% and 85.11% on the 16 and 17 datasets, respectively, which proves that DualGCN-MIL has a higher accuracy in WSI classification. Implementation can be obtained from https://***/UnmatchedKatana/DualGCN-MIL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint regression and learning from pairwise rankings for personalized image aesthetic assessment

引用

Computational Visual Media 2021年第2期7卷 241-252页

作者： Jin Zhou Qing Zhang Jian-Hao Fan Wei Sun Wei-Shi Zheng School of Electronics and Information Technology Sun Yat-sen UniversityGuangzhou 510006China. School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education(Sun Yat-sen University)Guangzhou 510006China Peng Cheng Laboratory Shenzhen 518000China

Recent image aesthetic assessment methods have achieved remarkable progress due to the emergence of deep convolutional neural networks(CNNs).However,these methods focus primarily on predicting generally perceived preference of an image,making them usually have limited practicability,since each user may have completely different preferences for the same *** address this problem,this paper presents a novel approach for predicting personalized image aesthetics that fit an individual user’s personal *** achieve this in a coarse to fine manner,by joint regression and learning from pairwise ***,we first collect a small subset of personal images from a user and invite him/her to rank the preference of some randomly sampled image *** then search for the K-nearest neighbors of the personal images within a large-scale dataset labeled with average human aesthetic scores,and use these images as well as the associated scores to train a generic aesthetic assessment model by CNN-based ***,we fine-tune the generic model to accommodate the personal preference by training over the rankings with a pairwise hinge *** demonstrate that our method can effectively learn personalized image aesthetic preferences,clearly outperforming state-of-the-art ***,we show that the learned personalized image aesthetic benefits a wide variety of applications.

关键词： s personalized image aesthetic assessment deep convolutional neural networks pairwise ranking regression

来源：评论

学校读者我要写书评

暂无评论

Structure-Augment based Long-Tailed Knowledge Graph Completion Model

Structure-Augment based Long-Tailed Knowledge Graph Completi...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jianrong Wang Yi Tang Dejun Hou Jinchi Wang Zechen Meng Tianyi Xu 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 Information and Network Center Tianjin University Tianjin China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The application of knowledge graph completion in industry and the Internet of Things involves various aspects, ranging from improving production efficiency to providing intelligent decision support. During the pursuit of constructing a knowledge graph, information for the graph is obtained from textual documents and online web pages. The extraction of information from documents is incomplete due to the limited information, so the knowledge graph needs to be completed. The knowledge graph completion model maps triples into different vector spaces for representation, but it still has the following shortcomings: 1) the textual encoder lacks of structured knowledge, 2) the distribution of relationships is long-tailed, with the model predominantly predicting more frequent relationships. In this paper, we propose structure-augment based long-tailed knowledge graph completion model (SALT-KGC) to deal with the two issues. To tackle the first problem, we partition each triple into two asymmetric parts as in translation-based graph embedding approach. We encode both parts using a Siamese-style textual encoder. Our model employs both classifier and spatial measurement for representation and structure learning respectively, in order to increase the structured knowledge of encoders. To tackle the second problem, we implement the focal loss to solve the problem of imbalance between positive and negative samples and focus on hard examples. Moreover, we develop a self-adaptive ensemble scheme to further improve the performance by incorporating from an existing graph embedding model. The SALT-KGC model achieves state-of-the-art performance on two widely-used public datasets.

关键词： Representation learning Computational modeling Web pages Knowledge graphs Tail Production Predictive models

来源：评论

学校读者我要写书评

暂无评论

Fast Peer Adaptation with Context-aware Exploration 41

Fast Peer Adaptation with Context-aware Exploration

引用

41st International Conference on machine Learning, ICML 2024

作者： Ma, Long Wang, Yuanfei Zhong, Fangwei Zhu, Song-Chun Wang, Yizhou Academy for Advanced Interdisciplinary Studies Peking University China Nat'l Key Laboratory of General Artificial Intelligence BIGAI&PKU China Center on Frontiers of Computing Studies School of Computer Science Peking University China School of Intelligence Science and Technology Peking University China Inst. for Artificial Intelligence Peking University China Nat'l Eng. Research Center of Visual Technology Peking University China

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation. However, exploring the strategies of unknown peers is difficult, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods1 Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Can Encrypted Images Still Train Neural Networks? Investigating Image Information and Random Vortex Transformation

arXiv

引用

arXiv 2024年

作者： Cao, Xiao-Kai Mo, Wen-Jin Wang, Chang-Dong Lai, Jian-Huang Huang, Qiong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China College of Mathematics and Informatics South China Agricultural University Guangzhou China

Vision is one of the essential sources through which humans acquire information. To simulate this biological characteristic, researchers have proposed models such as Convolutional Neural Networks and Vision Transformers to mimic the human visual system’s processing of visual tasks like image classification. These models have achieved significant success in experiments. However, there has been limited theoretical analysis of the variation in information content during image processing. This is not an insignificant task, as it plays a crucial guiding role in image feature extraction, image quality assessment, and the design of image encryption algorithms. In this paper, we establish a novel framework for measuring image information content to evaluate the variation in information content during image transformations. Within this framework, we design a nonlinear function to calculate the neighboring information content of pixels at different distances, and then use this information to measure the overall information content of the image. Hence, we define a function to represent the variation in information content during image transformations. Additionally, we utilize this framework to prove the conclusion that swapping the positions of any two pixels reduces the image’s information content. Furthermore, based on the aforementioned framework, we propose a novel image encryption algorithm called Random Vortex Transformation. This algorithm encrypts the image using random functions while preserving the neighboring information of the pixels. The encrypted images are difficult for the human eye to distinguish, yet they allow for direct training of the encrypted images using machine learning methods. Experimental verification demonstrates that training on the encrypted dataset using ResNet and Vision Transformers only results in a decrease in accuracy ranging from 0.3% to 6.5% compared to the original data, while ensuring the security of the data. Furthermore, there is a po

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mastering Cooperative Driving Strategy in Complex Scenarios using Multi-Agent Reinforcement Learning

Mastering Cooperative Driving Strategy in Complex Scenarios ...

引用

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

作者： Liang, Qingyi Jiang, Zhengmin Yin, Jianwen Xu, Kun Pan, Zhongming Dang, Shaobo Liu, Jia Southern University of Science and Technology Shenzhen518055 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350327182

With the advent of machine learning, several autonomous driving tasks have become easier to accomplish. Nonetheless, the proliferation of autonomous vehicles in urban traffic scenarios has precipitated other challenges, such as cooperative driving. Multi-Agent Reinforcement Learning (MARL) approaches have emerged as a promising solution, as they can successfully address the challenge by simulating the interactive relationship among autonomous vehicles (AVs). In this paper, we leverage Social Value Orientation to depict the behavioral tendencies of AVs, thereby enhancing the performance of MARL approaches. We also incorporate different scale features in the policy network to strengthen its representation ability. Moreover, effective reward functions are designed based on traffic efficiency, comfort, safety, and strategy. Finally, we validate our approach in an open-source autonomous driving simulator. Simulation results indicate that our proposed approach outperforms IPPO and MAPPO algorithms in terms of success rate, route completion rate, crash rate, and other metrics. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Novel Duo-Stage driven Deep Neural Network Approach for Mitigating Electrode Shift Impact on Myoelectric Pattern Recognition Systems

A Novel Duo-Stage driven Deep Neural Network Approach for Mi...

引用

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Kulwa, Frank Samuel, Oluwarotimi Williams Asogbon, Mojisola Grace Oyemakinde, Tolulope Tofunmi Obe, Olumide Olayinka Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems SIAT-CAS China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Guangdong Shenzhen518055 China University of Derby School of Computing and Engineering DerbyDE22 3AW United Kingdom Federal University of Technology Department of Computer Science Akure Nigeria

ISBN: (纸本)9781665493840

A major barrier to the commercialization of pattern recognition (PR)-based myoelectric prostheses is the lack of robustness to confounding factors such as electrode shift which has been lingering for years. To overcome this challenge, a novel Duo-Stage Convolutional Neural Network (DS-CNN) is proposed. The DS-CNN is comprised of two cascaded stages in which the first stage deciphers the occurrence of a particular kind of shift upon which a requisite CNN model is triggered in the second stage for accurate decoding of individual motion intent, which is necessary for initiating robust control of the prostheses. The proposed scheme works on raw EMG signals as input which reduces the preprocessing time that would be required in conventional machine learning-based PR schemes, to effectively mitigate both transverse and longitudinal shifts using the same network architecture. This approach was validated for four distinct electrode shift conditions (with shifts in the range of 7.50mm-10.05mm) in a dataset obtained from 18 able-bodied subjects that performed 8 classes of targeted hand gestures. The experimental results show that the proposed dual-stage driven deep neural network model can adequately resolve the effects of electrode shift with classification accuracy near the No-shift scenario ( © 2023 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

FIRE: a dataset for feedback integration and refinement evaluation of multimodal models 24

FIRE: a dataset for feedback integration and refinement eval...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UD-TN: A comprehensive ultrasound dataset for benign and malignant thyroid nodule classification

引用

Intelligent Oncology 2025年第2期1卷 176-187页

作者： Jialin Zhu Xuzhou Fu Zhiqiang Liu Luchen Chang Xuewei Li Jie Gao Ruiguo Yu Xi Wei Department of Diagnostic and Therapeutic Ultrasonography Tianjin Medical University Cancer Institute & Hospital National Clinical Research Center for Cancer Key Laboratory of Cancer Prevention and Therapy Tianjin’s Clinical Research Center for Cancer Tianjin 300060 China College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin Key Laboratory of Advanced Networking Tianjin University Tianjin 300350 China

The automatic classification of thyroid nodules in ultrasound images is a critical research focus in medical imaging. However, publicly available thyroid ultrasound datasets remain scarce. In this study, we developed the Ultrasound Dataset for Thyroid Nodules (UD-TN), a comprehensive dataset containing 10,495 labeled images classified as benign or malignant based on pathology-confirmed results. To establish a benchmark, we proposed the Thyroid Ultrasound Image Neural Network (ThyUNet), a deep learning model designed for accurate nodule classification. By incorporating high-resolution feature enhancement, instance normalization, and dilated convolutions into residual blocks, ThyUNet excels in extracting fine-grained features, particularly for small nodules. Experimental results demonstrate that ThyUNet achieves state-of-the-art performance, with an accuracy of 89.7%, a sensitivity of 0.879, and a specificity of 0.910 on the testing set. These results surpass those of other advanced architectures, highlighting the model’s effectiveness. UD-TN and ThyUNet contribute significantly to advancing intelligent medical diagnostics. Dataset details and access instructions are available at https://***/18811755633/Sample-of-UD-TN .

关键词：

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：