Exploiting Saliency for Object Segmentation From Image Level Labels

Seong Joon Oh, Rodrigo Benenson, Anna Khoreva, Zeynep Akata, Mario Fritz, Bernt Schiele; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4410-4419

Abstract


There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object regions can be obtained from image-level labels. Without additional information, obtaining the full extent of the object is an inherently ill-posed problem due to co-occurrences. We propose using a saliency model as additional information and hereby exploit prior knowledge on the object extent and image statistics. We show how to combine both information sources in order to recover 80% of the fully supervised performance - which is the new state of the art in weakly supervised training for pixel-wise semantic labelling.

Related Material


[pdf] [supp] [arXiv] [poster]
[bibtex]
@InProceedings{Oh_2017_CVPR,
author = {Joon Oh, Seong and Benenson, Rodrigo and Khoreva, Anna and Akata, Zeynep and Fritz, Mario and Schiele, Bernt},
title = {Exploiting Saliency for Object Segmentation From Image Level Labels},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}