On learning to localize objects with minimal supervision - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2014

On learning to localize objects with minimal supervision

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.
Fichier principal
Vignette du fichier
hyun_icml14.pdf (1.24 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-00996849 , version 1 (27-05-2014)

Identifiers

  • HAL Id : hal-00996849 , version 1

Cite

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⟩
1047 View
567 Download

Share

More