Weakly supervised semantic segmentation using web-crawled videos

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 49
  • Download : 0
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the entire object area. Our goal is to overcome this limitation with no additional human intervention by retrieving videos relevant to target class labels from web repository, and generating segmentation labels from the retrieved videos to simulate strong supervision for semantic segmentation. During this process, we take advantage of image classification with discriminative localization technique to reject false alarms in retrieved videos and identify relevant spatio-temporal volumes within retrieved videos. Although the entire procedure does not require any additional supervision, the segmentation annotations obtained from videos are sufficiently strong to learn a model for semantic segmentation. The proposed algorithm substantially outperforms existing methods based on the same level of supervision and is even as competitive as the approaches relying on extra annotations.
Publisher
IEEE Computer Society and the Computer Vision Foundation (CVF)
Issue Date
2017-07-21
Language
English
Citation

30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp.2224 - 2232

DOI
10.1109/CVPR.2017.239
URI
http://hdl.handle.net/10203/269611
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0