检索结果-内蒙古大学图书馆

Instance-aware graph convolutional network for multi-label classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Yun Zhang, Tong Cui, Zhen Xu, Chunyan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Graph convolutional neural network (GCN) has effectively boosted the multi-label image recognition task by introducing label dependencies based on statistical label co-occurrence of data. However, in previous methods, label correlation is computed based on statistical information of data and therefore the same for all samples, and this makes graph inference on labels insufficient to handle huge variations among numerous image instances. In this paper, we propose an instance-aware graph convolutional neural network (IA-GCN) framework for multi-label classification. As a whole, two fused branches of sub-networks are involved in the framework: a global branch modeling the whole image and a region-based branch exploring dependencies among regions of interests (ROIs). For label diffusion of instance-awareness in graph convolution, rather than using the statistical label correlation alone, an image-dependent label correlation matrix (LCM), fusing both the statistical LCM and an individual one of each image instance, is constructed for graph inference on labels to inject adaptive information of label-awareness into the learned features of the model. Specifically, the individual LCM of each image is obtained by mining the label dependencies based on the scores of labels about detected ROIs. In this process, considering the contribution differences of ROIs to multi-label classification, variational inference is introduced to learn adaptive scaling factors for those ROIs by considering their complex distribution. Finally, extensive experiments on MS-COCO and VOC datasets show that our proposed approach outperforms existing state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

DONet: Dual-octave network for fast MR image reconstruction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Feng, Chun-Mei Yang, Zhanyuan Fu, Huazhu Xu, Yong Yang, Jian Shao, Ling Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China School of Automation Engineering University of Electronic Science and Technology of China 611731 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates PCA Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjiang University of Science and Technology Nanjiang210094 China Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatialfrequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of Dual-Octave convolutions (Dual-OctConv), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary), and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intra-group information updating and inter-group information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: (i) It encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity. (ii) The dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse. (iii) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction. © 2021, CC BY.

关键词： Magnetic resonance imaging

Adversarial semantic data augmentation for human pose estimation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Bin, Yanrui Cao, Xuan Chen, Xinya Ge, Yanhao Tai, Ying Wang, Chengjie Li, Jilin Huang, Feiyue Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab China

Human pose estimation is the task of localizing body keypoints from still images. The state-of-the-art methods suffer from insufficient examples of challenging cases such as symmetric appearance, heavy occlusion and nearby person. To enlarge the amounts of challenging cases, previous methods augmented images by cropping and pasting image patches with weak semantics, which leads to unrealistic appearance and limited diversity. We instead propose Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity. Furthermore, we propose Adversarial Semantic Data Augmentation (ASDA), which exploits a generative network to dynamiclly predict tailored pasting configuration. Given off-the-shelf pose estimation network as discriminator, the generator seeks the most confusing transformation to increase the loss of the discriminator while the discriminator takes the generated sample as input and learns from it. The whole pipeline is optimized in an adversarial manner. State-of-the-art results are achieved on challenging benchmarks. The code has been publicly available at https://***/Binyr/ASDA. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantics

Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Cheng, Mingmei Hui, Le Xie, Jin Yang, Jian Kong, Hui PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

关键词： Semantic Segmentation

Assignment problem based deep embedding 1

学校读者我要写书评

暂无评论

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Zheng, Ruishen Xie, Jin Qian, Jianjun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

How to measure the similarity of samples is a fundamental problem in many computer vision tasks such as retrieval and clustering. Due to the rapid development of deep neural networks, deep metric learning has been widely studied. Some studies focus on the hard sample mining strategy for triplet loss. We observe that hard mining strategies are also vital for contrastive loss. But the hardest mining strategy for contrastive loss is sensitive to outliers. In this paper, based on combinatorial information of sample pairs, we propose a novel linear assignment problem based hard sample mining strategy for contrastive loss to learn feature embeddings. Specifically, our method can assign 0/1 weight to sample pairs for the hard sample selection by maximizing a linear assignment loss and ensure that each sample is only included by one pair for the optimization. Our method can obtain the state-of-the-art performance on the CUB-200-2011, Cars196, and In-shop datasets with the GoogLeNet network. © Springer Nature Switzerland AG 2019.

关键词： Combinatorial optimization

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Deng, Tianpeng Huang, Yanqi Han, Guoqiang Shi, Zhenwei Lin, Jiatai Dou, Qi Liu, Zaiyi Guo, Xiao-Jing Chen, C.L. Philip Han, Chu The School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China The Department of Computer Science and Engineering The Chinese University of Hong Kong 999077 Hong Kong The Department of Breast Pathology and Lab Tianjin Medical University Cancer Institute and Hospital National Clinical Research Center of Cancer Key Laboratory of Cancer Prevention and Therapy Tianjin Tianjin’s Clinical Research Center for Cancer Key Laboratory of Breast Cancer Prevention and Therapy Tianjin Medical University Ministry of Education Tianjin300060 China

Histopathological tissue classification is a fundamental task in computational pathology. Deep learning-based models have achieved superior performance but centralized training with data centralization suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, but existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their practicability in the real-world clinical scenario. In this paper, we propose a universal and lightweight federated learning framework, named Federated Deep-Broad Learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply associating a pre-trained deep learning feature extractor, a fast and lightweight broad learning inference system and a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6GB to only 276.5KB per client using the ResNet-50 backbone at 50-round training. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://***/tianpeng-deng/FedDBL. © 2023, CC BY.

关键词： Tissue

Multi-scale dynamic feature encoding network for image demoiréing 17

学校读者我要写书评

暂无评论

Multi-scale dynamic feature encoding network for image demoi...

17th IEEE/CVF International Conference on Computer Vision Workshop, ICCVW 2019

作者： Cheng, Xi Fu, Zhenyong Yang, Jian PCA Lab Key Lab of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781728150239

The prevalence of digital sensors, such as digital cameras and mobile phones, simplifies the acquisition of photos. Digital sensors, however, suffer from producing Moire when photographing objects having complex textures, which deteriorates the quality of photos. Moire spreads across various frequency bands of images and is a dynamic texture with varying colors and shapes, which pose two main challenges in demoireing - an important task in image restoration. In this paper, towards addressing the first challenge, we design a multi-scale network to process images at different spatial resolutions, obtaining features in different frequency bands, and thus our method can jointly remove moire in different frequency bands. Towards solving the second challenge, we propose a dynamic feature encoding module (DFE), embedded in each scale, for dynamic texture. Moire pattern can be eliminated more effectively via *** proposed method, termed Multi-scale convolutional network with Dynamic feature encoding for image DeMoireing (MDDM), can outperform the state of the arts in fidelity as well as perceptual on benchmarks. © 2019 IEEE.

关键词： image reconstruction

Exploiting learnable joint groups for hand pose estimation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Moran Gao, Yuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent AI Lab United States

In this paper, we propose to estimate 3D hand pose by recovering the 3D coordinates of joints in a group-wise manner, where less-related joints are automatically categorized into different groups and exhibit different features. This is different from the previous methods where all the joints are considered holistically and share the same feature. The benefits of our method are illustrated by the principle of multi-task learning (MTL), i.e., by separating less-related joints into different groups (as different tasks), our method learns different features for each of them, therefore efficiently avoids the negative transfer (among less related tasks/groups of joints). The key of our method is a novel binary selector that automatically selects related joints into the same group. We implement such a selector with binary values stochastically sampled from a Concrete distribution, which is constructed using Gumbel softmax on trainable parameters. This enables us to preserve the differentiable property of the whole network. We further exploit features from those less-related groups by carrying out an additional feature fusing scheme among them, to learn more discriminative features. This is realized by implementing multiple 1x1 convolutions on the concatenated features, where each joint group contains a unique 1x1 convolution for feature fusion. The detailed ablation analysis and the extensive experiments on several benchmark datasets demonstrate the promising performance of the proposed method over the state-of-the-art (SOTA) methods. Besides, our method achieves top-1 among all the methods that do not exploit the dense 3D shape labels on the most recently released FreiHAND competition at the submission date. The source code and models are available at https://***/moranli-aca/LearnableGroups-Hand. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Multi-task learning for object keypoints detection and classification

学校读者我要写书评

暂无评论

Pattern Recognition Letters 2020年 130卷 182-188页

作者： Jie Xu Lin Zhao Shanshan Zhang Chen Gong Jian Yang PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing 210094 China State Key Laboratory of Integrated Services Networks Xidian Univeristy Xi’an 710071 China

Object keypoints detection and classification are both central research topics in computer vision . Due to their wide range potential applications in the real world, substantial efforts have been taken to advance their performance. However, these two related tasks are mainly treated separately in previous works. We argue that keypoints detection and classification can be complementary tasks and beneficial to each other. Knowing the category of a object is able to reduce the searching space of keypoints detection models and facilitate more precise localization . On the other hand, having the knowledge of object keypoints can make classification models pay more attention on areas that are more associated with the object, which will inevitably promote classification accuracy . Embracing this observation, we propose to model keypoints detection and classification in a multi-task learning framework. Specifically, a multi-task deep network is designed and trained to conduct both tasks, where we devise the model structure delicately to carry out sufficient training of both tasks. Extensive experiments are set up on the AIFASHION DATASET and Human3.6M DATASET to validate our proposal, we show that our algorithm outperforms separate models trained individually on each task.

关键词：