TY - GEN
T1 - Augmented feedback in semantic segmentation under image level supervision
AU - QI, Xiaojuan
AU - LIU, Zhengzhe
AU - SHI, Jianping
AU - ZHAO, Hengshuang
AU - JIA, Jiaya
PY - 2016
Y1 - 2016
N2 - Training neural networks for semantic segmentation is data hungry. Meanwhile annotating a large number of pixel-level segmentation masks needs enormous human effort. In this paper, we propose a framework with only image-level supervision. It unifies semantic segmentation and object localization with important proposal aggregation and selection modules. They greatly reduce the notorious error accumulation problem that commonly arises in weakly supervised learning. Our proposed training algorithm progressively improves segmentation performance with augmented feedback in iterations. Our method achieves decent results on the PASCAL VOC 2012 segmentation data, outperforming previous image-level supervised methods by a large margin.
AB - Training neural networks for semantic segmentation is data hungry. Meanwhile annotating a large number of pixel-level segmentation masks needs enormous human effort. In this paper, we propose a framework with only image-level supervision. It unifies semantic segmentation and object localization with important proposal aggregation and selection modules. They greatly reduce the notorious error accumulation problem that commonly arises in weakly supervised learning. Our proposed training algorithm progressively improves segmentation performance with augmented feedback in iterations. Our method achieves decent results on the PASCAL VOC 2012 segmentation data, outperforming previous image-level supervised methods by a large margin.
KW - Image-level supervision
KW - Proposal aggregation
KW - Semantic segmentation
KW - Weakly supervised learning
UR - http://www.scopus.com/inward/record.url?scp=84990038459&partnerID=8YFLogxK
U2 - 10.1007/978-3-319-46484-8_6
DO - 10.1007/978-3-319-46484-8_6
M3 - Conference paper (refereed)
AN - SCOPUS:84990038459
SN - 9783319464831
T3 - Lecture Notes in Computer Science
SP - 90
EP - 105
BT - Computer Vision : ECCV 2016 : 14th European Conference Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VIII
A2 - LEIBE, Bastian
A2 - MATAS, Jiri
A2 - SEBE, Nicu
A2 - WELLING, Max
PB - Springer
ER -