Augmented Feedback in Semantic Segmentation Under Image Level Supervision
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractTraining 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.
Acceptance Date08/10/2016
All Author(s) ListXiaojuan Qi, Zhengzhe Liu, Jianping Shi, Hengshuang Zhao, Jiaya Jia
Name of ConferenceEuropean Conference on Computer Vision
Start Date of Conference11/10/2016
End Date of Conference14/10/2016
Place of ConferenceAmsterdam
Country/Region of ConferenceNetherlands
Year2016
Month10
Day8
PublisherSpringer International Publishing
Pages99 - 105
LanguagesEnglish-United States
Keywordsweakly supervised learning, semantic segmentation, image-level supervision, proposal aggregation

Last updated on 2018-22-01 at 12:53