Augmented feedback in semantic segmentation under image level supervision

Xiaojuan QI*, Zhengzhe LIU, Jianping SHI, Hengshuang ZHAO, Jiaya JIA

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

96 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationComputer Vision : ECCV 2016 : 14th European Conference Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part VIII
EditorsBastian LEIBE, Jiri MATAS, Nicu SEBE, Max WELLING
PublisherSpringer
Pages90-105
Number of pages16
ISBN (Electronic)9783319464848
ISBN (Print)9783319464831
DOIs
Publication statusPublished - 2016
Externally publishedYes

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume9912
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameImage Processing, Computer Vision, Pattern Recognition, and Graphics
PublisherSpringer
ISSN (Print)3004-9946
ISSN (Electronic)3004-9954

Funding

This work is supported by a grant from the Research Grants Council of the Hong Kong SAR (project No. 2150760) and by the National Science Foundation China, under Grant 61133009.

Keywords

  • Image-level supervision
  • Proposal aggregation
  • Semantic segmentation
  • Weakly supervised learning

Fingerprint

Dive into the research topics of 'Augmented feedback in semantic segmentation under image level supervision'. Together they form a unique fingerprint.

Cite this