Learn to Propagate Reliably on Noisy Affinity Graphs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkOpen-Ended Question AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting
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 i…
Graph MatchingRobust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach
Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite …
Graph structure learningRepresentation LearningGraph LearningTackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation (WSSS) with image-level labels intends to achieve dense tasks without laborious annotations. However, due to the ambiguous contexts and fuzzy regions, the performance of WSSS, espe…
DiversitySemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationAffinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
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 s…
Box-supervised Instance SegmentationGraph Neural NetworkInstance SegmentationModel Optimization+4Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels
Noisy labels collected with limited annotation cost prevent medical image segmentation algorithms from learning precise semantic correlations. Previous segmentation arts of learning with noisy labels merely perform a pix…
Image SegmentationLearning with noisy labelsMedical Image SegmentationSegmentation+1