检索结果-内蒙古大学图书馆

Graph Contrastive Learning with Learnable Graph Augmentation

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Learnable Graph Augmentation

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

作者： Xinyan Pu Ke Zhang Huazhong Shu Jean Louis Coatrieux Youyong Kong Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China LTSI Universit de Rennes 1 Rennes France Centre de Recherche en Information BioMdicale Sino-Franais Rennes France

Graph contrastive learning has gained popularity due to its success in self-supervised graph representation learning. Augmented views in contrastive learning greatly determine the quality of the learned representations. Handcrafted data augmentations in previous work require tedious trial-and- errors per dataset, which is time-consuming and resource-intensive. Here, we propose a Graph Contrastive learning framework with Learnable graph Augmentation called GraphCLA. Specifically, learnable graph augmentation trains augmented views by minimizing the mutual information (MI) between the input graphs and their augmented graphs. This paper designs a kernel contrastive loss function based on an end-to-end differentiable graph kernel to learn augmented views. In addition, this paper utilizes a min-max optimization strategy to learn challenging augmented graphs and to learn discriminative representations adversarially. Finally, we compared GraphCLA with state-of-the-art self-supervised learning baselines and experimentally validate the effectiveness of GraphCLA.

关键词： Representation learning Self-supervised learning Signal processing Benchmark testing Acoustics Kernel Speech processing

Polyp Segmentation Neural Network with Simple Encoding Structure and Reverse Attention Module

学校读者我要写书评

暂无评论

Polyp Segmentation Neural Network with Simple Encoding Struc...

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Jie Wang Zuoyong Li Haiping Xu Xuesong Cheng Shenghua Teng College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China Fujian Key Laboratory of Medical Big Data Engineering Fujian Provincial Hospital Fuzhou China College of Mathematics and Data Science Minjiang University Fuzhou China

Colorectal cancer is a common malignancy. In colonoscopy images, computer-assisted polyp segmentation helps doctors diagnose and treat disorders more precisely. In recent years, some methods based on deep convolutional neural networks have made significant breakthroughs in this task. However, only a few algorithms explicitly consider the effect of light intensity on segmentation performance, which results in algorithms needing to be more robust for complex samples. This paper proposes a neural network combining a simple encoding structure with a reverse attention module. Specifically, the model uses HarDNet68 as the backbone network, adds a camouflage identification module (CIM) to enhance the capture of polyp details on the underlying features, and finally utilizes adaptive feature fusion with the reverse attention module (RAM). The proposed model effectively addresses the challenge of poor segmentation quality in colonoscopy images caused by inconsistent illumination. Extensive experiments on five datasets show that the proposed model performs well in polyp segmentation.

关键词：

Deep self-representative concept factorization network for representation learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhang, Yan Zhang, Zhao Zhang, Zheng Zhao, Mingbo Zhang, Li Zha, Zhengjun Wang, Meng School of Computer Science and Technology Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China Hefei University of Technology Hefei China Shenzhen China Department of Electronic Engineering City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong School of Information Science and Technology University of Science and Technology of China Hefei China

— In this paper, we investigate the unsupervised deep representation learning issue and technically propose a novel framework called Deep Self-representative Concept Factorization Network (DSCF-Net), for clustering deep features. To improve the representation and clustering abilities, DSCF-Net explicitly considers discovering hidden deep semantic features, enhancing the robustness properties of the deep factorization to noise and preserving the local manifold structures of deep features. Specifically, DSCF-Net seamlessly integrates the robust deep concept factorization, deep self-expressive representation and adaptive locality preserving feature learning into a unified framework. To discover hidden deep representations, DSCF-Net designs a hierarchical factorization architecture using multiple layers of linear transformations, where the hierarchical representation is performed by formulating the problem as optimizing the basis concepts in each layer to improve the representation indirectly. DSCF-Net also improves the robustness by subspace recovery for sparse error correction firstly and then performs the deep factorization in the recovered visual subspace. To obtain locality-preserving representations, we also present an adaptive deep self-representative weighting strategy by using the coefficient matrix as the adaptive reconstruction weights to keep the locality of representations. Extensive comparison results with several other related models show that DSCF-Net delivers state-of-the-art performance on several public databases. Copyright © 2019, The Authors. All rights reserved.

关键词： Factorization

Learning Hierarchical Graph Representation for Image Manipulation Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pan, Wenyan Zhou, Zhili Ling, Miaogen Geng, Xin Wu, Q.M. Jonathan School of Computer and Software & Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China School of Computer Science and Engineering Southeast University Nanjing China Department of Electrical and Computer Engineering University of Windsor WindsorON Canada

The objective of image manipulation detection is to identify and locate the manipulated regions in the images. Recent approaches mostly adopt the sophisticated Convolutional Neural Networks (CNNs) to capture the tampering artifacts left in the images to locate the manipulated regions. However, these approaches ignore the feature correlations, i.e., feature inconsistencies, between manipulated regions and non-manipulated regions, leading to inferior detection performance. To address this issue, we propose a hierarchical Graph Convolutional Network (HGCN-Net), which consists of two parallel branches: the backbone network branch and the hierarchical graph representation learning (HGRL) branch for image manipulation detection. Specifically, the feature maps of a given image are extracted by the backbone network branch, and then the feature correlations within the feature maps are modeled as a set of fully-connected graphs for learning the hierarchical graph representation by the HGRL branch. The learned hierarchical graph representation can sufficiently capture the feature correlations across different scales, and thus it provides high discriminability for distinguishing manipulated and non-manipulated regions. Extensive experiments on four public datasets demonstrate that the proposed HGCN-Net not only provides promising detection accuracy, but also achieves strong robustness under a variety of common image attacks in the task of image manipulation detection, compared to the state-of-the-arts. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

Analysis of Big Data Complex Network Structure Based on Fuzzy Clustering Algorithm

学校读者我要写书评

暂无评论

Analysis of Big Data Complex Network Structure Based on Fuzz...

Networking, Communications and information technology (NetCIT), International Conference on

作者： Fu Shanshan Ruan Zhiqiang Center of Modem Education Technology and Information Management Minjiang University Fujian China College of Computer and Control Engineering Minjiang University Fujian China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fujian China Digital Fujian IoT Laboratory of Intelligent Production Fujian China

ISBN: (纸本)9781665400718

In the era of artificial intelligence with big data as the background, the statistical analysis method based on complex network has become a research hotspot and actively promoted the development of big data visualization. Complex network is a new discipline developed by cross research with other disciplines. Its network topology has obvious clustering characteristics, that is, complex network cluster structure. Together with small world and scale-free, it is called the three most important and basic attributes of complex network topology. The fundamental purpose of complex network clustering algorithm is to detect the actual network cluster structure in complex network, which has very important practical value for mining the cluster structure in network and understanding its characteristics, and is conducive to understanding the functions of network, such as predicting the development of complex network, analyzing the behavior of social network, discovering hot topics on network, etc. This paper combines the methods and ideas of complex network analysis, carries out the method design and research of organization analysis, and tries to solve the relationship and characteristics of inter departmental cooperation within the organization.

关键词： Visualization Data analysis Heuristic algorithms Data visualization Clustering algorithms Complex networks Organizations

Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Guoan Li, Juncheng Gao, Guangwei Lu, Huimin Yang, Jian Yue, Dong The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210023 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210049 China The Kyushu Institute of Technology Kitakyushu804-8550 Japan The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210049 China

In the past decade, convolutional neural networks (CNNs) have shown prominence for semantic segmentation. Although CNN models have very impressive performance, the ability to capture global representation is still insufficient, which results in suboptimal results. Recently, Transformer achieved huge success in NLP tasks, demonstrating its advantages in modeling long-range dependency. Recently, Transformer has also attracted tremendous attention from computer vision researchers who reformulate the image processing tasks as a sequence-to-sequence prediction but resulted in deteriorating local feature details. In this work, we propose a lightweight real-time semantic segmentation network called LETNet. LETNet combines a U-shaped CNN with Transformer effectively in a capsule embedding style to compensate for respective deficiencies. Meanwhile, the elaborately designed Lightweight Dilated Bottleneck (LDB) module and Feature Enhancement (FE) module cultivate a positive impact on training from scratch simultaneously. Extensive experiments performed on challenging datasets demonstrate that LETNet achieves superior performances in accuracy and efficiency balance. Specifically, It only contains 0.95M parameters and 13.6G FLOPs but yields 72.8% mIoU at 120 FPS on the Cityscapes test set and 70.5% mIoU at 250 FPS on the CamVid test dataset using a single RTX 3090 GPU. Source code will be available at https://***/IVIPLab/LETNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

Deep progressive reinforcement learning-based flexible resource scheduling framework for IRS and UAV-assisted MEC system

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dong, Li Jiang, Feibo Wang, Minjie Peng, Yubo Li, Xiaolong School of Computer Science Hunan University of Technology and Business Changsha China Xiangjiang Laboratory Changsha China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China College of Information Science and Engineering Hunan Normal University Changsha China

The intelligent reflection surface (IRS) and unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system is widely used in temporary and emergency scenarios. Our goal is to minimize the energy consumption of the MEC system by jointly optimizing UAV locations, IRS phase shift, task offloading, and resource allocation with a variable number of UAVs. To this end, we propose a Flexible REsource Scheduling (FRES) framework by employing a novel deep progressive reinforcement learning which includes the following innovations: Firstly, a novel multi-task agent is presented to deal with the mixed integer nonlinear programming (MINLP) problem. The multi-task agent has two output heads designed for different tasks, in which a classified head is employed to make offloading decisions with integer variables while a fitting head is applied to solve resource allocation with continuous variables. Secondly, a progressive scheduler is introduced to adapt the agent to the varying number of UAVs by progressively adjusting a part of neurons in the agent. This structure can naturally accumulate experiences and be immune to catastrophic forgetting. Finally, a light taboo search (LTS) is introduced to enhance the global search of the FRES. The numerical results demonstrate the superiority of the FRES framework which can make real-time and optimal resource scheduling even in dynamic MEC systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

FTG: Score-based black-box watermarking by fragile trigger generation for deep model integrity verification

学校读者我要写书评

暂无评论

Journal of information and Intelligence 2024年第1期2卷 28-41页

作者： Heng Yin Zhaoxia Yin Zhenzhe Gao Hang Su Xinpeng Zhang Bin Luo Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui UniversityHefei 230000China Shanghai key Laboratory of Multidimensional Information Processing East China Normal UniversityShanghai 200241China School of Communication and Electronic Engineering East China Normal UniversityShanghai 200241China Department of Computer Science and Technology Tsinghua UniversityBeijing 100000China School of Computer Science and Technology Fudan UniversityShanghai 200241China

Deep neural networks(DNNs)are widely used in real-world applications,thanks to their exceptional performance in image ***,their vulnerability to attacks,such as Trojan and data poison,can compromise the integrity and stability of DNN ***,it is crucial to verify the integrity of DNN models to ensure their *** research on model watermarking for integrity detection has encountered the issue of overexposure of model parameters during embedding and extraction of the *** address this problem,we propose a novel score-based black-box DNN fragile watermarking framework called fragile trigger generation(FTG).The FTG framework only requires the prediction probability distribution of the final output of the classifier during the watermarking *** generates different fragile samples as the trigger,based on the classification prediction probability of the target classifier and a specified prediction probability mask to watermark *** prediction probability masks can promote the generation of fragile samples in corresponding distribution *** whole watermarking process does not affect the performance of the target *** verifying the watermarking information,the FTG only needs to compare the prediction results of the model on the samples with the previous *** a result,the required model parameter information is reduced,and the FTG only needs a few samples to detect slight modifications in the *** results demonstrate the effectiveness of our proposed method and show its superiority over related *** FTG framework provides a robust solution for verifying the integrity of DNN models,and its effectiveness in detecting slight modifications makes it a valuable tool for ensuring the security and stability of DNN applications.

关键词： Neural network Sensitive sample Fragile watermarking Model integrity Fragile trigger

White blood cell segmentation based on dual path network and channel attention

学校读者我要写书评

暂无评论

White blood cell segmentation based on dual path network and...

International Conference on information Science and Control Engineering (ICISCE)

作者： Yan Lu Xinrong Cao Zuoyong Li Tao Wang Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China College of Mathematics and Computer Science Fuzhou University Fuzhou China Fuzhou Digital Healthcare Industry Technology Innovation Center Fuzhou China

White blood cell (WBC, leukocyte) in blood smear image plays a crucial role in the diagnosis of many blood diseases. WBC segmentation is an important preprocessing step in blood disease diagnosis. However, due to some factors such as different dying technologies and different WBC appearances, WBC segmentation is still challenging. To improve accuracy of WBC segmentation, we propose an end-to-end WBC segmentation network. Specifically, we first introduce Dual Path Network (DPN) as a context-aware feature encoder to extract multi-scale image features. Then, we use a channel attention module to capture the interdependencies between channel maps, and further enhance feature representation capability of the proposed network. Finally, we reconstruct WBC feature maps by a feature decoder, and use skip connections to reduce image information loss. Experimental results on three datasets show that the proposed method obtains higher segmentation accuracy than the other methods.

关键词： White blood cells Image segmentation information science Control engineering Fuses Feature extraction Decoding