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.
@article{arxiv.1403.1024,
title = {On learning to localize objects with minimal supervision},
author = {Hyun Oh Song and Ross Girshick and Stefanie Jegelka and Julien Mairal and Zaid Harchaoui and Trevor Darrell},
journal= {arXiv preprint arXiv:1403.1024},
year = {2014}
}