View Decomposition and Adversarial for Semantic Segmentation

	View Decomposition and Adversarial for Semantic Segmentation
	He Guan; Zhaoxiang Zhang
	2018-06
会议日期	August, 28-31, 2018
会议地点	Nanjing
关键词	View Decomposition Adversarial Semantic Segmentation
英文摘要	The adversarial training strategy has been effectively validated because it maintains high-level contextual consistency. However, limited to the weak capability of a simple discriminator, it is irresponsible and unreasonable to identify one from the sample source at a time. We introduce a novel discriminator module called Multi-View Decomposition which transforms the discriminator role from general teacher to specific adversary. The proposed module separates single sample into a series of class inter-independent streams and extracts corresponding features from current mask. The key insight in the MVD module is that the final source decision can be aggregated from all available views rather than a harsh critic. Our experimental results demonstrate that the proposed module can improve performance on PASCAL VOC 2012 and PASCAL Context dataset further.
URL标识	查看原文
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/21599]
专题	自动化研究所_类脑智能研究中心
作者单位	1.University of Chinese Academy of Sciences 2.Research Center for Brain-inspired Intelligence, CASIA 3.CAS Center for Excellence in Brain Science and Intelligence Technology 4.National Laboratory of Pattern Recognition, CASIA
推荐引用方式 GB/T 7714	He Guan,Zhaoxiang Zhang. View Decomposition and Adversarial for Semantic Segmentation[C]. 见:. Nanjing. August, 28-31, 2018.