Skip to Main content Skip to Navigation
Conference papers

On learning to localize objects with minimal supervision

Hyun Oh Song 1 Ross Girshick 1 Stefanie Jegelka 2 Julien Mairal 3, * Zaid Harchaoui 3 Trevor Darrell 1
* Corresponding author
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download
Contributor : Julien Mairal Connect in order to contact the contributor
Submitted on : Tuesday, May 27, 2014 - 9:38:37 AM
Last modification on : Thursday, January 20, 2022 - 5:28:03 PM
Long-term archiving on: : Wednesday, August 27, 2014 - 11:01:21 AM


Files produced by the author(s)


  • HAL Id : hal-00996849, version 1



Hyun Oh Song, Ross Girshick, Stefanie Jegelka, Julien Mairal, Zaid Harchaoui, et al.. On learning to localize objects with minimal supervision. ICML - 31st International Conference on Machine Learning, Jun 2014, Beijing, China. pp.1611-1619. ⟨hal-00996849⟩



Les métriques sont temporairement indisponibles