Object localization in ImageNet by looking out of the window

Alexander Vezhnevets and Vittorio Ferrari

Abstract

We propose a method for annotating the location of objects in ImageNet. Traditionally, this is cast as an image window classification problem, where each window is considered independently and scored based on its appearance alone. Instead, we propose a method which scores each candidate window in the context of all other windows in the image, taking into account their similarity in appearance space as well as their spatial relations in the image plane. We devise a fast and exact procedure to optimize our scoring function over all candidate windows in an image, and we learn its parameters using structured output regression. We demonstrate on 92000 images from ImageNet that this significantly improves localization over recent techniques that score windows in isolation.

Session

Poster 1

Files

Extended Abstract (PDF, 2M)
Paper (PDF, 4M)

DOI

10.5244/C.29.27
https://dx.doi.org/10.5244/C.29.27

Citation

Bibtex

@inproceedings{BMVC2015_27,
	title={Object localization in ImageNet by looking out of the window},
	author={Alexander Vezhnevets and Vittorio Ferrari},
	year={2015},
	month={September},
	pages={27.1-27.12},
	articleno={27},
	numpages={12},
	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.29.27},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.27}
}