View Decomposition and Adversarial for Semantic Segmentation

CASIA OpenIR > 模式识别实验室

	View Decomposition and Adversarial for Semantic Segmentation
	He Guan; Zhaoxiang Zhang
	2018-06
会议名称	The 15th Pacific Rim International Conference on Artificial Intelligence
会议日期	August, 28-31, 2018
会议地点	Nanjing
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.
关键词	View Decomposition Adversarial Semantic Segmentation
URL	查看原文
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21599
专题	模式识别实验室
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],2018.

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
PRICAI2018.pdf（872KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载