检索结果-南通市图书馆

Few-Shot Graph Classification with Structural-Enhanced contrastive learning for Graph Data Copyright Protection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第2期29卷 605-616页

作者： Kainan Zhang DongMyung Shin Daehee Seo Zhipeng Cai Department of Computer Science Georgia State UniversityAtlantaGA 30303USA LSWare Inc. Seoul 08504Republic of Korea College of Intelligence Information Engineering Sangmyung UniversitySeoul 03016Republic of Korea

Open-source licenses can promote the development of machine learning by allowing others to access,modify,and redistribute the training dataset.However,not all open-source licenses may be appropriate for data sharing,as some may not provide adequate protections for sensitive or personal information such as social network data.Additionally,some data may be subject to legal or regulatory restrictions that limit its sharing,regardless of the licensing model used.Hence,obtaining large amounts of labeled data can be difficult,time-consuming,or expensive in many real-world scenarios.Few-shot graph classification,as one application of meta-learning in supervised graph learning,aims to classify unseen graph types by only using a small amount of labeled data.However,the current graph neural network methods lack full usage of graph structures on molecular graphs and social network datasets.Since structural features are known to correlate with molecular properties in chemistry,structure information tends to be ignored with sufficient property information provided.Nevertheless,the common binary classification task of chemical compounds is unsuitable in the few-shot setting requiring novel labels.Hence,this paper focuses on the graph classification tasks of a social network,whose complex topology has an uncertain relationship with its nodes'attributes.With two multi-class graph datasets with large node-attribute dimensions constructed to facilitate the research,we propose a novel learning framework that integrates both meta-learning and contrastive learning to enhance the utilization of graph topological information.Extensive experiments demonstrate the competitive performance of our framework respective to other state-of-the-art methods.

关键词： few-shot learning contrastive learning data copyright protection

contrastive learning for Blind Super-Resolution via A Distortion-Specific Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第1期10卷 78-89页

作者： Xinya Wang Jiayi Ma Junjun Jiang the Electronic Information School Wuhan UniversityWuhan 430072China IEEE the School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China

Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.

关键词： Blind super-resolution contrastive learning deep learning image super-resolution(SR)

Cross-modal contrastive learning for Generalizable and Efficient Image-text Retrieval

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2023年第4期20卷 569-582页

作者： Haoyu Lu Yuqi Huo Mingyu Ding Nanyi Fei Zhiwu Lu Gaoling School of Artificial Intelligence Renmin University of ChinaBeijing100872China The University of Hong Kong Hong Kong999077China

Cross-modal image-text retrieval is a fundamental task in bridging vision and language. It faces two main challenges that are typically not well addressed in previous works. 1) Generalizability: Existing methods often assume a strong semantic correlation between each text-image pair, which are thus difficult to generalize to real-world scenarios where the weak correlation dominates. 2) Efficiency: Many latest works adopt the single-tower architecture with heavy detectors, which are inefficient during the inference stage because the costly computation needs to be repeated for each text-image pair. In this work, to overcome these two challenges, we propose a two-tower cross-modal contrastive learning (CMCL) framework. Specifically, we first devise a two-tower architecture, which enables a unified feature space for the text and image modalities to be directly compared with each other, alleviating the heavy computation during inference. We further introduce a simple yet effective module named multi-grid split (MGS) to learn fine-grained image features without using detectors. Last but not the least, we deploy a cross-modal contrastive loss on the global image/text features to learn their weak correlation and thus achieve high generalizability. To validate that our CMCL can be readily generalized to real-world scenarios, we construct a large multi-source image-text dataset called weak semantic correlation dataset (WSCD). Extensive experiments show that our CMCL outperforms the state-of-the-arts while being much more efficient.

关键词： Image-text retrieval multimodal modeling contrastive learning weak correlation computer vision

EFECL:Feature encoding enhancement with contrastive learning for indoor 3D object detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 875-892页

作者： Yao Duan Renjiao Yi Yuanming Gao Kai Xu Chenyang Zhu School of Computing National University of Defense TechnologyChangsha 410000China

Good proposal initials are critical for 3D object detection applications.However,due to the significant geometry variation of indoor scenes,incomplete and noisy proposals are inevitable in most cases.Mining feature information among these“bad”proposals may mislead the detection.contrastive learning provides a feasible way for representing proposals,which can align complete and incomplete/noisy proposals in feature space.The aligned feature space can help us build robust 3D representation even if bad proposals are given.Therefore,we devise a new contrast learning framework for indoor 3D object detection,called EFECL,that learns robust 3D representations by contrastive learning of proposals on two different levels.Specifically,we optimize both instance-level and category-level contrasts to align features by capturing instance-specific characteristics and semantic-aware common patterns.Furthermore,we propose an enhanced feature aggregation module to extract more general and informative features for contrastive learning.Evaluations on ScanNet V2 and SUN RGB-D benchmarks demonstrate the generalizability and effectiveness of our method,and our method can achieve 12.3%and 7.3%improvements on both datasets over the benchmark alternatives.The code and models are publicly available at https://***/YaraDuan/EFECL.

关键词： indoor scene object detection contrastive learning feature enhancement

A Review of Predictive and contrastive Self-supervised learning for Medical Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2023年第4期20卷 483-513页

作者： Wei-Chien Wang Euijoon Ahn Dagan Feng Jinman Kim Biomedical and Multimedia Information Technology(BMIT)Research Group School of Computer ScienceThe University of SydneySydneyNSW2006Australia College of Science and Engineering James Cook UniversityCairnsQLD4811Australia

Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks. But, the application of deep learning in medical image analysis is limited by the scarcity of high-quality annotated medical imaging data. An emerging solution is self-supervised learning (SSL), among which contrastive SSL is the most successful approach to rivalling or outperforming supervised learning. This review investigates several state-of-the-art contrastive SSL algorithms originally on natural images as well as their adaptations for medical images, and concludes by discussing recent advances, current limitations, and future directions in applying contrastive SSL in the medical domain.

关键词： Self-supervised learning(SSL) contrastive learning deep learning medical image analysis computer vision

What makes for uniformity for non-contrastive self-supervised learning?

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2022年第10期65卷 2399-2408页

作者： WANG YinQuan ZHANG XiaoPeng TIAN Qi Lü JinHu Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Huawei Inc. Shenzhen 518128China School of Automation Science and Electrical Engineering State Key Laboratory of Software Development EnvironmentBeihang UniversityBeijing 100191China

Recent advances in self-supervised learning(SSL) have made remarkable progress, especially for contrastive methods that target pulling two augmented views of one image together and pushing the views of all other images away. In this setting, negative pairs play a key role in avoiding collapsed representation. Recent studies, such as those on bootstrap your own latent(BYOL)and SimSiam, have surprisingly achieved a comparable performance even without contrasting negative samples. However, a basic theoretical issue for SSL arises: how can different SSL methods avoid collapsed representation, and is there a common design principle? In this study, we look deep into current non-contrastive SSL methods and analyze the key factors that avoid collapses.To achieve this goal, we present a new indicator of uniformity metric and study the local dynamics of the indicator to diagnose collapses in different scenarios. Moreover, we present some principles for choosing a good predictor, such that we can explicitly control the optimization process. Our theoretical analysis result is validated on some widely used benchmarks spanning differentscale datasets. We also compare recent SSL methods and analyze their commonalities in avoiding collapses and some ideas for future algorithm designs.

关键词： contrastive learning self-supervised learning representation uniformity dynamics

A Memory-Guided Anomaly Detection Model with contrastive learning for Multivariate Time Series

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第11期77卷 1893-1910页

作者： Wei Zhang Ping He Ting Li Fan Yang Ying Liu School of Electronic and Information Engineering Hebei University of TechnologyTianjin300401China School of Artificial Intelligence Hebei University of TechnologyTianjin300401China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China

Some reconstruction-based anomaly detection models in multivariate time series have brought impressive performance advancements but suffer from weak generalization ability and a lack of anomaly identification.These limitations can result in the misjudgment of models,leading to a degradation in overall detection performance.This paper proposes a novel transformer-like anomaly detection model adopting a contrastive learning module and a memory block(CLME)to overcome the above limitations.The contrastive learning module tailored for time series data can learn the contextual relationships to generate temporal fine-grained representations.The memory block can record normal patterns of these representations through the utilization of attention-based addressing and reintegration mechanisms.These two modules together effectively alleviate the problem of generalization.Furthermore,this paper introduces a fusion anomaly detection strategy that comprehensively takes into account the residual and feature spaces.Such a strategy can enlarge the discrepancies between normal and abnormal data,which is more conducive to anomaly identification.The proposed CLME model not only efficiently enhances the generalization performance but also improves the ability of anomaly detection.To validate the efficacy of the proposed approach,extensive experiments are conducted on well-established benchmark datasets,including SWaT,PSM,WADI,and MSL.The results demonstrate outstanding performance,with F1 scores of 90.58%,94.83%,91.58%,and 91.75%,respectively.These findings affirm the superiority of the CLME model over existing stateof-the-art anomaly detection methodologies in terms of its ability to detect anomalies within complex datasets accurately.

关键词： Anomaly detection multivariate time series contrastive learning memory network

Height estimation from single aerial imagery using contrastive learning based multi-scale refinement network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2023年第1期16卷 2322-2340页

作者： Wufan Zhao Hu Ding Jiaming Na Mengmeng Li Dirk Tiede Geomatics Section Department of Civil EngineeringFaculty of Engineering TechnologyKU LeuvenBelgium School of Geography South China Normal UniversityGuangzhouPeople’s Republic of China College of Civil Engineering Nanjing Forestry UniversityNanjingPeople’s Republic of China Academy of Digital China(Fujian) Fuzhou UniversityFuzhouPeople’s Republic of China Department of Geoinformatics(Z_GIS) Faculty of Digital and Analytical SciencesParis Lodron University of SalzburgSalzburgAustria

Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.

关键词： Height estimation aerial imagery digital surface models contrastive learning local implicit constrain

SimCLIC:A Simple Framework for contrastive learning of Image Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science and Information 2023年第2期11卷 204-218页

作者： Han YANG Jun LI College of Computer Science&Technology Qingdao UniversityQingdao 266000China

contrastive learning,a self-supervised learning method,is widely used in image representation learning.The core idea is to close the distance between positive sample pairs and increase the distance between negative sample pairs in the representation space.Siamese networks are the most common structure among various current contrastive learning models.However,contrastive learning using positive and negative sample pairs on large datasets is computationally expensive.In addition,there are cases where positive samples are mislabeled as negative samples.contrastive learning without negative sample pairs can still learn good representations.In this paper,we propose a simple framework for contrastive learning of image classification(SimCLIC).SimCLIC simplifies the Siamese network and is able to learn the representation of an image without negative sample pairs and momentum encoders.It is mainly by perturbing the image representation generated by the encoder to generate different contrastive views.We apply three representation perturbation methods,namely,history representation,representation dropoput,and representation noise.We conducted experiments on several benchmark datasets to compare with current popular models,using image classification accuracy as a measure,and the results show that our SimCLIC is competitive.Finally,we did ablation experiments to verify the effect of different hyperparameters and structures on the model effectiveness.

关键词： contrastive learning representation learning image classification