Joint Calibration for Semantic Segmentation

Holger Caesar, Jasper Uijlings and Vittorio Ferrari

Abstract

Semantic segmentation is the task of assigning a class-label to each pixel in an image. We propose a region-based semantic segmentation framework which handles both full and weak supervision, and addresses three common problems: (1) Objects occur at multiple scales and therefore we should use regions at multiple scales. However, these regions are overlapping which creates conflicting class predictions at the pixel-level. (2) Class frequencies are highly imbalanced in realistic datasets. (3) Each pixel can only be assigned to a single class, which creates competition between classes. We address all three problems with a joint calibration method which optimizes a multi-class loss defined over the final pixel-level output labeling, as opposed to simply region classification. Our method outperforms the state-of-the-art on the popular SIFT Flow [17] dataset in both the fully and weakly supervised setting.

Session

Poster 1

Files

Extended Abstract (PDF, 534K)
Paper (PDF, 2M)

DOI

10.5244/C.29.29
https://dx.doi.org/10.5244/C.29.29

Citation

Bibtex

@inproceedings{BMVC2015_29,
	title={Joint Calibration for Semantic Segmentation},
	author={Holger Caesar and Jasper Uijlings and Vittorio Ferrari},
	year={2015},
	month={September},
	pages={29.1-29.13},
	articleno={29},
	numpages={13},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.29},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.29}
}