Digging into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation

doi:10.1109/ACCESS.2020.2975022

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 光电探测技术研究室（三室）

	Digging into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation
	Chen, Zhenghao 1; Zhang, Rui 1,2; Zhang, Gang 1,2; Ma, Zhenhuan 1,2; Lei, Tao 1
刊名	IEEE Access
	2020-07-12
卷号	8 页码:41830-41837
关键词	Semantics Image segmentation Training Semisupervised learning Pipelines Standards Reliability Sematic segmentation semi-supervised learning computer vision deep learning
ISSN号	2169-3536
DOI	10.1109/ACCESS.2020.2975022
文献子类	期刊论文
英文摘要	The capability to understand visual scenes with limited labeled data has been widely concerned in the field of computer vision. Although semi-supervised learning for image classification has been extensively studied in some cases, semantic segmentation with limited data has only recently gained attention. In this work, we follow the standard semi-supervised segmentation pipeline for image classification and propose a two-branch network that can encode strong and pseudo label spaces respectively, extracting reliable supervision information from pseudo-labels to assist in training network with strong labels. Our method outperforms previous semi-supervised methods with limited annotation cost. On standard benchmark PASCAL VOC 2012 for semi-supervised semantic segmentation, the proposed approach gains fresh state-of-the-art performance. © 2013 IEEE.
出版地	PISCATAWAY
WOS研究方向	Computer Science ; Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000525388000005
内容类型	期刊论文
源URL	[http://ir.ioe.ac.cn/handle/181551/10056]
专题	光电技术研究所_光电探测技术研究室（三室）
作者单位	1.Chinese Academy of Sciences, Institute of Optics and Electronics, Chengdu; 610209, China; 2.School of Optoelectronics, University of Chinese Academy of Sciences, Beijing; 100049, China
推荐引用方式 GB/T 7714	Chen, Zhenghao,Zhang, Rui,Zhang, Gang,et al. Digging into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation[J]. IEEE Access,2020,8:41830-41837.
APA	Chen, Zhenghao,Zhang, Rui,Zhang, Gang,Ma, Zhenhuan,&Lei, Tao.(2020).Digging into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation.IEEE Access,8,41830-41837.
MLA	Chen, Zhenghao,et al."Digging into Pseudo Label: A Low-Budget Approach for Semi-Supervised Semantic Segmentation".IEEE Access 8(2020):41830-41837.