Incremental learning of latent structural SVM for weakly supervised image classification

Thibaut Durand 1 Nicolas Thome 1 Matthieu Cord 1 David Picard 2
1 MLIA - Machine Learning and Information Access
LIP6 - Laboratoire d'Informatique de Paris 6
2 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
Abstract : Visual learning with weak supervision is a promising re-search area, since it offers the possibility to build large image datasets at reasonable cost. In this paper, we address the prob-lem of weakly supervised object detection, where the goal is to predict the label of the image using object position as latent variable. We propose a new method that builds upon the La-tent Structural SVM (LSSVM) formalism. Specifically, we introduce an original coarse-to-fine approach that limits the evolution of the latent parameter subspace. This incremental strategy drives the learning towards better solutions, provid-ing a model with increased predictive accuracy. In addition, this leads to a significant speed up during learning and infer-ence compared to standard sliding window methods. Experi-ments carried out on Mammal dataset validate the good per-formances and fast training of the method compared to state-of-the-art works.
Document type :
Conference papers
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01077058
Contributor : Thibaut Durand <>
Submitted on : Thursday, October 23, 2014 - 5:04:49 PM
Last modification on : Thursday, March 21, 2019 - 1:12:49 PM

File

durand_ICIP2014_ILSSVM.pdf
Files produced by the author(s)

Identifiers

Citation

Thibaut Durand, Nicolas Thome, Matthieu Cord, David Picard. Incremental learning of latent structural SVM for weakly supervised image classification. IEEE International Conference on Image Processing, Oct 2014, Paris, France. pp.4246-4250, ⟨10.1109/ICIP.2014.7025862⟩. ⟨hal-01077058⟩

Share

Metrics

Record views

262

Files downloads

238