检索结果-内蒙古大学图书馆

Node transfer with graph contrastive learning for class-imbalanced node classification

学校读者我要写书评

暂无评论

Neural Networks 2025年 190卷

作者： Yangding Li Xiangchao Zhao Yangyang Zeng Hao Feng Jiawei Chai Hao Xie Shaobin Fu Shichao Zhang College of Information Science and Engineering Hunan Normal University Changsha China Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China

In graph representation learning, the class imbalance problem is a significant challenge that has received much attention from academics. Although current approaches have shown promising results, they have not adequately addressed the problems of node quantity imbalance and feature space imbalance in datasets. This research presents a node transfer with graph contrastive learning framework (NT-GCL) that aims to improve the representation capabilities of graph neural networks for minority classes nodes by balancing node quantity and feature space distributions. First, the proposed node transfer algorithm redistributes misclassified nodes from majority classes to achieve a balanced distribution of node quantity and feature space. This approach effectively prevents the feature space of minority classes from being compressed by majority classes during information propagation, further mitigating potential imbalance issues. Subsequently, the self-supervised contrastive learning strategy is employed to train the model without relying on labels, reducing the bias introduced by labeled data. Experiments conducted with various encoders on six public datasets demonstrate that NT-GCL exhibits strong competitiveness in class-imbalanced node classification.

关键词：

Self-regulated learning for egocentric video activity anticipation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Qi, Zhaobo Wang, Shuhui Su, Chi Su, Li Huang, Qingming Tian, Qi The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Kingsoft Cloud Beijing100085 China Cloud BU Huawei Technologies Shenzhen518129 China

Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a simple and effective Self-Regulated Learning framework, which aims to regulate the intermediate representation consecutively to produce representation that (a) emphasizes the novel information in the frame of the current time-stamp in contrast to previously observed content, and (b) reflects its correlation with previously observed frames. The former is achieved by minimizing a contrastive loss, and the latter can be achieved by a dynamic reweighing mechanism to attend to informative frames in the observed content with a similarity comparison between feature of the current frame and observed frames. The learned final video representation can be further enhanced by multi-task learning which performs joint feature learning on the target activity labels and the automatically detected action and object class tokens. SRL sharply outperforms existing state-of-the-art in most cases on two egocentric video datasets and two third-person video datasets. Its effectiveness is also verified by the experimental fact that the action and object concepts that support the activity semantics can be accurately identified. © 2021, CC BY.

关键词： Semantics

PSpan: Mining frequent subnets of petri nets

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lu, Ruqian Zhang, Shuhan Academy of Mathematics and Systems Science Key Lab of MADIS Chineses Academy Science China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

This paper proposes for the first time an algorithm PSpan for mining frequent complete subnets from a set of Petri nets. We introduced the concept of complete subnets and the net graph representation. PSpan transforms Petri nets in net graphs and performs sub-net graph mining on them, then transforms the results back to frequent subnets. PSpan follows the pattern growth approach and has similar complexity like gSpan in graph mining. Experiments have been done to confirm PSpan's reliability and complexity. Besides C/E nets, it applies also to a set of other Petri net subclasses. Copyright © 2021, The Authors. All rights reserved.

关键词： Petri nets

Clean-label Backdoor Attacks on Video Recognition Models

学校读者我要写书评

暂无评论

Clean-Label Backdoor Attacks on Video Recognition Models

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Shihao Zhao Xingjun Ma Xiang Zheng James Bailey Jingjing Chen Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University School of Computing and Information Systems The University of Melbourne

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and have raised severe security concerns in real-world applications. Thus far, backdoor research has mostly been conducted in the image domain with image classification models. In this paper, we show that existing image backdoor attacks are far less effective on videos, and outline 4 strict conditions where existing attacks are likely to fail: 1) scenarios with more input dimensions (eg. videos), 2) scenarios with high resolution, 3) scenarios with a large number of classes and few examples per class (a ``sparse dataset"), and 4) attacks with access to correct labels (eg. clean-label attacks). We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions. We show on benchmark video datasets that our proposed backdoor attack can manipulate state-of-the-art video models with high success rates by poisoning only a small proportion of training data (without changing the labels). We also show that our proposed backdoor attack is resistant to state-of-the-art backdoor defense/detection methods, and can even be applied to improve image backdoor attacks. Our proposed video backdoor attack not only serves as a strong baseline for improving the robustness of video models, but also provides a new perspective for more understanding more powerful backdoor attacks.

关键词： Training Data models Toxicology Perturbation methods Training data Image resolution Pipelines

The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Alibaba Group China School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University China Key Laboratory of Big Data Mining and Knowledge Management CAS China Peng Cheng Laboratory China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a diversity control regularization term to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML. © 2022, CC BY-NC-SA.

关键词： Embeddings

Noise Robust Hard Example Mining for Human Detection with Efficient Depth-Thermal Fusion

学校读者我要写书评

暂无评论

Noise Robust Hard Example Mining for Human Detection with Ef...

International Conference on Automatic Face and Gesture Recognition

作者： Zijian Zhao Jie Zhang Shiguang Shan Key Lab of Intelligent Information Processing Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

Identity-preserving human detection is important for the privacy-protecting applications. IPHD [1] is a newly collected identity-preserving dataset that only contains depth and thermal images, which have much less information than RGB images. While less information and weakly labeled ground-truth boxes make it difficult to locate the objects correctly. In this paper, we adopt an efficient depth-thermal fusion approach to combine these two different inputs and enhance the representation. Moreover, a noise robust hard example mining algorithm is proposed to deal with weakly labeled data. The experiments show that our single model with single scale testing can get the AP=88.1 at IoU=0.5, which is a significant improvement compared with other competition results.

关键词： Noise robustness Feature extraction Training Head Thermal noise Kernel Detectors

LasHeR: A large-scale high-diversity benchmark for RGBT tracking

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Chenglong Xue, Wanlin Jia, Yaqing Qu, Zhichen Luo, Bin Tang, Jin Sun, Dengdi Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

RGBT tracking receives a surge of interest in the computer vision community, but this research field lacks a large-scale and high-diversity benchmark dataset, which is essential for both the training of deep RGBT trackers and the comprehensive evaluation of RGBT tracking methods. To this end, we present a Large-scale High-diversity benchmark for short-term RGBT tracking (LasHeR) in this work. LasHeR consists of 1224 visible and thermal infrared video pairs with more than 730K frame pairs in total. Each frame pair is spatially aligned and manually annotated with a bounding box, making the dataset well and densely annotated. LasHeR is highly diverse capturing from a broad range of object categories, camera viewpoints, scene complexities and environmental factors across seasons, weathers, day and night. We conduct a comprehensive performance evaluation of 12 RGBT tracking algorithms on the LasHeR dataset and present detailed analysis. In addition, we release the unaligned version of LasHeR to attract the research interest for alignment-free RGBT tracking, which is a more practical task in real-world applications. The datasets and evaluation protocols are available at: https://***/mmic-lcl/Datasets-and-benchmark-code. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

Global-Local Attention Network for Semantic Segmentation in Aerial Images

学校读者我要写书评

暂无评论

Global-Local Attention Network for Semantic Segmentation in ...

International Conference on Pattern Recognition

作者： Minglong Li Lianlei Shan Xiaobin Li Yang Bai Dengji Zhou Weiqiang Wang Ke Lv Bin Luo Si-Bao Chen University of Chinese Academy of Sciences Beijing China Aerospace Information Research Institute Chinese Academy of Science Beijing China MOE Key Lab of Signal Processing and Intelligent Computing School of Computer Science and Technology Anhui University Hefei China

Errors in semantic segmentation could be classified into two types: the large area misclassification and inaccurate local boundaries. Previously attention-based methods typically capture rich global contextual information, which benefits the large area classification but cannot address the local errors of boundaries. In this paper, we propose a Global-Local Attention Network (GLANet) which can simultaneously consider the global context and local details. Specifically, our GLANet consists of two branches: (1) the global attention branch and (2) local attention branch. Furthermore, three different modules are embedded in GLANet for respectively modelling the semantic interdependencies in spatial, channel and boundary dimension. Lastly, we merge the outputs of different branches to enhance the feature representation further, resulting in more precise segmentation. Overall, the proposed method achieves the competitive segmentation accuracy on two public aerial image datasets, bringing significant improvements over the existing baselines.

关键词： Image segmentation Image color analysis Image edge detection Semantics Vegetation mapping Vegetation Pattern recognition

An Image Denoising Method Based on Deep Residual GAN 4

学校读者我要写书评

暂无评论

An Image Denoising Method Based on Deep Residual GAN

2020 4th International Workshop on Advanced Algorithms and Control Engineering, IWAACE 2020

作者： Wang, Ziyuan Wang, Lidan Duan, Shukai Li, Yunfei Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China Schoolof Electronic and Information Engineering Southwest University Chongqing400715 China College of Artificiall Intelligence Southwest University Chongqing400715 China Braininspired Computing and Intelligent Control of Chongqing Key Lab Chongqing400715 China National and Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology Chongqing400715 China Chongqing Brain Science Collaborative Innovation Center Chongqing400715 China

As people come into contact with image data more often, high quality and clear images attract more attention. Many methods have been proposed to deal with image noise problem including deep learning (DL). However most of them is lack of capability when customers want more perceptual details of the image without information loss. In this paper, a deep residual network based on generative adversarial (GAN) network was proposed to complete the image denoising mission. Firstly, a generative-adversarial network structure based on residual blocks was designed. Secondly, a refined loss function was given to train the GAN network. The well designed loss function can help the generated image to be very close to the clear counterpart (ground truth) while enhancing more details in colours and brightness. Finally, extensive experiments show that our network is not only convincing for images denoising, but also effective for other image process tasks, such as image defogging, medical CT denoising etc., presenting impressive and competitive effects. © Published under licence by IOP Publishing Ltd.

关键词： Image denoising