Search Machine Learning Repository:
On learning to localize objects with minimal supervision
Authors: Hyun O. Song, Ross Girshick, Stefanie Jegelka, Julien Mairal, Zaid Harchaoui and Trevor Darrell
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
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.
authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).