Back to Search Start Over

Augmented Feedback in Semantic Segmentation Under Image Level Supervision

Authors :
Jianping Shi
Hengshuang Zhao
Xiaojuan Qi
Zhengzhe Liu
Jiaya Jia
Source :
Computer Vision – ECCV 2016 ISBN: 9783319464831, ECCV (8)
Publication Year :
2016
Publisher :
Springer International Publishing, 2016.

Abstract

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.

Details

ISBN :
978-3-319-46483-1
ISBNs :
9783319464831
Database :
OpenAIRE
Journal :
Computer Vision – ECCV 2016 ISBN: 9783319464831, ECCV (8)
Accession number :
edsair.doi...........00f39ea5d6c20d49af0e5b832b34fb9f
Full Text :
https://doi.org/10.1007/978-3-319-46484-8_6