MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking

Résumé

In this work, we propose a novel Weakly Supervised Learning (WSL) framework dedicated to learn discriminative part detectors from images annotated with a global label. Our WSL method encompasses three main contributions. Firstly, we introduce a new structured output latent variable model, Minimum mAximum lateNt sTRucturAl SVM (MANTRA), which prediction relies on a pair of latent variables: $h^+$ (resp. $h^-$) provides positive (resp. negative) evidence for a given output $y$. Secondly, we instantiate MANTRA for two different visual recognition tasks: multi-class classification and ranking. For ranking, we propose efficient solutions to exactly solve the inference and the loss-augmented problems. Finally, extensive experiments highlight the relevance of the proposed method: MANTRA outperforms state-of-the art results on five different datasets.
Fichier principal
Vignette du fichier
mantra_iccv2015.pdf (1.78 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01343784 , version 1 (12-07-2016)

Identifiants

  • HAL Id : hal-01343784 , version 1

Citer

Thibaut Durand, Nicolas Thome, Matthieu Cord. MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking. IEEE International Conference on Computer Vision (ICCV15), Dec 2015, Santiago, Chile. ⟨hal-01343784⟩
227 Consultations
177 Téléchargements

Partager

Gmail Facebook X LinkedIn More