Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

Arslan Chaudhry, Puneet Kumar Dokania and Philip Torr

Abstract

We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task. We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance. First, we propose a simple yet powerful hierarchical approach to discover the class-agnostic salient regions, obtained using a salient object detector, which otherwise would be ignored. Second, we use fully convolutional attention maps to reliably localize the class-specific regions in a given image. We combine these two cues to discover class-specific pixels which are then used as an approximate ground truth for training a CNN. While solving the weakly supervised semantic segmentation task, we ensure that the image-level classification task is also solved in order to enforce the CNN to assign at least one pixel to each object present in the image. Experimentally, on the PASCAL VOC12 val and test sets, we obtain the mIoU of 60.8% and 61.9%, achieving the performance gains of 5.1% and 5.2% compared to the published state-of-the-art results.

Session

Posters

Files

PDF iconPaper (PDF)

DOI

10.5244/C.31.20
https://dx.doi.org/10.5244/C.31.20

Citation

Arslan Chaudhry, Puneet Kumar Dokania and Philip Torr. Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 20.1-20.13. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_20,
                title={Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation},
                author={Arslan Chaudhry, Puneet Kumar Dokania and Philip Torr},
                year={2017},
                month={September},
                pages={20.1-20.13},
                articleno={20},
                numpages={13},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.20},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.20}
            }