Improving weakly-supervised object localization by micro-annotation

A. Kolesnikov, C. Lampert, in:, Proceedings of the British Machine Vision Conference 2016, BMVA Press, 2016, p. 92.1-92.12.


Conference Paper | Published | English
Department
Abstract
Weakly-supervised object localization methods tend to fail for object classes that consistently co-occur with the same background elements, e.g. trains on tracks. We propose a method to overcome these failures by adding a very small amount of model-specific additional annotation. The main idea is to cluster a deep network\'s mid-level representations and assign object or distractor labels to each cluster. Experiments show substantially improved localization results on the challenging ILSVC2014 dataset for bounding box detection and the PASCAL VOC2012 dataset for semantic segmentation.
Publishing Year
Date Published
2016-09-01
Proceedings Title
Proceedings of the British Machine Vision Conference 2016
Acknowledgement
This work was funded in parts by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no 308036. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this research.
Volume
2016-September
Page
92.1-92.12
Conference
BMVC: British Machine Vision Conference
Conference Location
York, United Kingdom
Conference Date
2016-09-19 – 2016-09-22
IST-REx-ID

Cite this

Kolesnikov A, Lampert C. Improving weakly-supervised object localization by micro-annotation. In: Proceedings of the British Machine Vision Conference 2016. Vol 2016-September. BMVA Press; 2016:92.1-92.12. doi:10.5244/C.30.92
Kolesnikov, A., & Lampert, C. (2016). Improving weakly-supervised object localization by micro-annotation. In Proceedings of the British Machine Vision Conference 2016 (Vol. 2016–September, p. 92.1-92.12). York, United Kingdom: BMVA Press. https://doi.org/10.5244/C.30.92
Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” In Proceedings of the British Machine Vision Conference 2016, 2016–September:92.1-92.12. BMVA Press, 2016. https://doi.org/10.5244/C.30.92.
A. Kolesnikov and C. Lampert, “Improving weakly-supervised object localization by micro-annotation,” in Proceedings of the British Machine Vision Conference 2016, York, United Kingdom, 2016, vol. 2016–September, p. 92.1-92.12.
Kolesnikov A, Lampert C. 2016. Improving weakly-supervised object localization by micro-annotation. Proceedings of the British Machine Vision Conference 2016. BMVC: British Machine Vision Conference vol. 2016–September. 92.1-92.12.
Kolesnikov, Alexander, and Christoph Lampert. “Improving Weakly-Supervised Object Localization by Micro-Annotation.” Proceedings of the British Machine Vision Conference 2016, vol. 2016–September, BMVA Press, 2016, p. 92.1-92.12, doi:10.5244/C.30.92.

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar