Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation

	Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation
	Ying P(应鹏); Liu J(刘静); Lu HQ(卢汉清); Ma SD(马颂德)
	2015-10
会议名称	ACM Multimedia Conference 2015
会议录名称	ACM Digital Library
会议日期	26 – 30,October,2015
会议地点	Brisbane, Queensland, Australia
摘要	; How to import image-level labels as weak supervision to direct the region-level labeling task is the core task of weaklysupervised semantic segmentation. In this paper, we focus on designing an effective but simple weakly-supervised constraint, and propose an exclusive constrained discriminative learning model for image semantic segmentation. To be specific, we employ a discriminative linear regression model to assign subsets of superpixels with different labels. During the assignment, we construct an exclusive weakly-supervised constraint term to suppress the labeling responses of each superpixel on the labels outside its parent image-level label set.. Besides, a spectral smoothing term is integrated to encourage that both visually and semantically similar superpixels have similar labels. Combining these terms, we formulate the problem as a convex objective function, which can be easily optimized via alternative iterations. Extensive experiments on MSRC-21 and LabelMe datasets demonstrate the effectiveness of the proposed model.
关键词	Semantic Segmentation Weak Supervision
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11598
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Ying P(应鹏)
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Ying P,Liu J,Lu HQ,et al. Exclusive Constrained Discriminative Learning for Weakly-Supervised Semantic Segmentation[C],2015.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
应鹏_MM.pdf（1375KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载