Learning from Weak and Noisy Labels for Semantic Segmentation

doi:10.1109/TPAMI.2016.2552172

CORC > 北京大学 > 信息科学技术学院

	Learning from Weak and Noisy Labels for Semantic Segmentation
	Lu, Zhiwu ; Fu, Zhenyong ; Xiang, Tao ; Han, Peng ; Wang, Liwei ; Gao, Xin
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2017
关键词	Semantic segmentation weakly supervised learning label noise reduction sparse learning SPARSE REPRESENTATION SCENE CLASSIFICATION
DOI	10.1109/TPAMI.2016.2552172
英文摘要	A weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these 'free' tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel L-1-optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the L-1-optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields stateof-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy.; National Natural Science Foundation of China [61573363, 61573026]; 973 Program of China [2014CB340403, 2015CB352502]; Fundamental Research Funds for the Central Universities; Research Funds of Renmin University of China [15XNLQ01]; IBM Global SUR Award Program; European Research Council FP7 Project SUNNY [313243]; KAUST; SCI(E); ARTICLE; 3; 486-500; 39
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/475431]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Lu, Zhiwu,Fu, Zhenyong,Xiang, Tao,et al. Learning from Weak and Noisy Labels for Semantic Segmentation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2017.
APA	Lu, Zhiwu,Fu, Zhenyong,Xiang, Tao,Han, Peng,Wang, Liwei,&Gao, Xin.(2017).Learning from Weak and Noisy Labels for Semantic Segmentation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.
MLA	Lu, Zhiwu,et al."Learning from Weak and Noisy Labels for Semantic Segmentation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017).