DMCA
On learning to localize objects with minimal supervision Hyun Oh Song
Cached
Download Links
| Citations: | 14 - 5 self |
BibTeX
@MISC{Girshick_onlearning,
author = {Ross Girshick and Stefanie Jegelka and Julien Mairal and Zaid Harchaoui and Trevor Darrell},
title = {On learning to localize objects with minimal supervision Hyun Oh Song},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a new method that achieves this goal with only image-level labels of whether the objects are present or not. Our approach combines a discriminative submodular cover problem for automatically discovering a set of positive object windows with a smoothed latent SVM formulation. The latter allows us to leverage efficient quasi-Newton optimization techniques. Our experiments demonstrate that the proposed approach provides a 50 % relative improvement in mean average precision over the current state-of-the-art on PASCAL VOC 2007 detection. 1.
Keyphrases
minimal supervision hyun oh song current state-of-the-art smoothed latent svm formulation minimal supervision new method image-level label discriminative submodular cover problem mean average precision pascal voc efficient quasi-newton optimization technique positive object computer vision relative improvement important problem
