On learning to localize objects with minimal supervision
This addresses the costly need for large fully annotated datasets in computer vision, offering a more efficient solution for object localization.
The paper tackles the problem of object localization with minimal supervision, using only image-level labels, and achieves a 50% relative improvement in mean average precision over the state-of-the-art on PASCAL VOC 2007 detection.
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.