Weakly Supervised RBM for Semantic Segmentation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Weakly Supervised RBM for Semantic Segmentation
	Yong Li; Jing Liu; Yuhang Wang; Hanqing Lu; Songde Ma
	2015
会议日期	July 25-31, 2015
会议地点	Buenos Aires, Argentina
关键词	无
英文摘要	In this paper, we propose a weakly supervised Restricted Boltzmann Machines (WRBM) approach to deal with the task of semantic segmentation with only image-level labels available. In WRBM, its hidden nodes are divided into multiple blocks, and each block corresponds to a specific label. Accordingly, semantic segmentation can be directly modeled by learning the mapping from visible layer to the hidden layer of WRBM. Specifically, based on the standard RBM, we import another two terms to make full use of image-level labels and alleviate the effect of noisy labels. First, we expect the hidden response of each superpixel is suppressed on the labels outside its parent image-level label set, and a non-image-level label suppression term is formulated to implicitly import the image-level labels as weak supervision. Second, semantic graph propagation is employed to exploit the cooccurrence between visually similar regions and labels. Besides, we deal with the problems of label imbalance and diverse backgrounds by adapting the block size to the label frequency and appending hidden response blocks corresponding to backgrounds respectively. Extensive experiments on two real-world datasets demonstrate the good performance of our approach compared with some state-of-the-art methods.
会议录	Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/11766]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
通讯作者	Jing Liu
推荐引用方式 GB/T 7714	Yong Li,Jing Liu,Yuhang Wang,et al. Weakly Supervised RBM for Semantic Segmentation[C]. 见:. Buenos Aires, Argentina. July 25-31, 2015.