首页/论文/2007.08802

arXiv 2007.088022020-07-17cs.CV

Learn to Propagate Reliably on Noisy Affinity Graphs

The Chinese University of Hong Kong（香港中文大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

Lei Yang, Qingqiu Huang, Huaiyi Huang, Linning Xu, Dahua Lin

备注：: 14 pages, 7 figures, ECCV 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models. Yet, how to propagate labels reliably, especially on a dataset with unknown outliers, remains an open question. Conventional methods such as linear diffusion lack the capability of handling complex graph structures and may perform poorly when the seeds are sparse. Latest methods based on graph neural networks would face difficulties on performance drop as they scale out to noisy graphs. To overcome these difficulties, we propose a new framework that allows labels to be propagated reliably on large-scale real-world data. This framework incorporates (1) a local graph neural network to predict accurately on varying local structures while maintaining high scalability, and (2) a confidence-based path scheduler that identifies outliers and moves forward the propagation frontier in a prudent way. Experiments on both ImageNet and Ms-Celeb-1M show that our confidence guided framework can significantly improve the overall accuracies of the propagated labels, especially when the graph is very noisy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation

DGIST（韩国基础科学研究院）；POSTECH（浦项科技大学）

The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between…

2018-04-09cs.CV

Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation

The University of Sydney（悉尼大学）；Murdoch University（莫道克大学）；Hong Kong University of Sciences and Technology（香港科技大学）；The University of Western Australia（西澳大学）

Semantic segmentation is a challenging task in the absence of densely labelled data. Only relying on class activation maps (CAM) with image-level labels provides deficient segmentation supervision. Prior works thus consider pre-trained models to produce coarse saliency maps to guide the generation of pseudo segmentation labels. However, the commonly used off-line heuristic generation process cannot fully exploit the benefits of these coarse saliency maps. Motivated by the significant inter-task correlation, we propose a novel weakly supervised multi-task framework termed as AuxSegNet, to lever…

2021-07-27cs.CV

CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation

Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）

Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplement…

2020-01-30cs.CV

从不确定性推理与亲和度多样化视角应对弱监督语义分割中的歧义问题

Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation

Academy for Engineering & Technology, Fudan University（复旦大学工程与技术学院）；Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；Shandong Computer Science Center（山东省计算机科学中心）

针对弱监督语义分割中的歧义问题，提出单阶段框架UniA，通过不确定性推理优化特征表示、亲和度多样化提升伪掩码质量，在多个数据集上表现优于同类方法。

2024-04-12cs.CV

A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting

Shanghai Jiao Tong University（上海交通大学）；IBM Research – China（IBM中国研究院）；INRIA（法国国家信息与自动化研究所）；Ecole Normale Superieure（巴黎高等师范学院）；East China Normal University（华东师范大学）

This paper addresses the problem of matching $N$ weighted graphs referring to an identical object or category. More specifically, matching the common node correspondences among graphs. This multi-graph matching problem involves two ingredients affecting the overall accuracy: i) the local pairwise matching affinity score among graphs; ii) the global matching consistency that measures the uniqueness of the pairwise matching results by different chaining orders. Previous studies typically either enforce the matching consistency constraints in the beginning of iterative optimization, which may pro…

2015-02-20cs.CV

Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

University of Liverpool（利物浦大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；University of Oxford（牛津大学）；University of Technology Sydney（悉尼科技大学）；Beijing Jiaotong University（北京交通大学）

Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose Affinity Attention Graph Neural Network ($A^2$GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our $A^2$G…

2021-06-08cs.CV

更多相关论文收起更多论文

辅助任务增强的双亲和学习用于弱监督语义分割

Auxiliary Tasks Enhanced Dual-affinity Learning for Weakly Supervised Semantic Segmentation

The University of Western Australia（西澳大学）；The University of Sydney（悉尼大学）；Murdoch University（莫道克大学）；HKUST（香港科技大学）

本文提出AuxSegNet+框架，以显著性检测和多标签分类为辅助任务，并通过跨任务双亲和学习细化CAM与伪标签，在PASCAL VOC和MS COCO上取得WSSS新最优结果。

2024-03-02cs.CV

Semi-supervised Learning on Graph with an Alternating Diffusion Process

Curtin University（科廷大学）

Graph-based semi-supervised learning usually involves two separate stages, constructing an affinity graph and then propagating labels for transductive inference on the graph. It is suboptimal to solve them independently, as the correlation between the affinity graph and labels are not fully exploited. In this paper, we integrate the two stages into one unified framework by formulating the graph construction as a regularized function estimation problem similar to label propagation. We propose an alternating diffusion process to solve the two problems simultaneously, which allows us to learn the…

2019-02-16cs.CV

从混沌到有序：无源域适应的标签传播视角

Chaos to Order: A Label Propagation Perspective on Source-Free Domain Adaptation

East China Normal University（华东师范大学）；Shanghai Normal University（上海师范大学）；Shenzhen University（深圳大学）；Shanghai Research Institute of Microwave Equipment（上海微波设备研究所）

本文提出 CtO 方法，通过自适应划分内部与离群样本、约束语义可信度并传播标签，提升无源域适应在三个基准上的性能。

2023-08-14cs.CV

Ensemble Teaching for Hybrid Label Propagation

Nanjing University of Science and Technology（南京理工大学）；Minjiang University（闽江学院）；University of Sydney（悉尼大学）；Carnegie Mellon University（卡内基梅隆大学）

Label propagation aims to iteratively diffuse the label information from labeled examples to unlabeled examples over a similarity graph. Current label propagation algorithms cannot consistently yield satisfactory performance due to two reasons: one is the instability of single propagation method in dealing with various practical data, and the other one is the improper propagation sequence ignoring the labeling difficulties of different examples. To remedy above defects, this paper proposes a novel propagation algorithm called hybrid diffusion under ensemble teaching (HyDEnT). Specifically, HyD…

2019-04-08cs.CV