Improving weakly-supervised object localization by micro-annotation Conference Paper

Author(s): Kolesnikov, Alexander; Lampert, Christoph H
Title: Improving weakly-supervised object localization by micro-annotation
Affiliation IST Austria
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.
Conference Title: BMVC: British Machine Vision Conference
Conference Dates: September 19-22, 2016
Conference Location: York, UK
ISBN: 1-901725-39-1
Publisher: BMVA Press  
Date Published: 2016-09-01
Copyright Statement: © 2016. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.
Notes: 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.
Open access: yes (repository)
IST Austria Authors
  1. Christoph Lampert
    87 Lampert
Related IST Austria Work