WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

Résumé

This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features. Our model is trained using only global image labels and is devoted to three main visual recognition tasks: image classification, weakly supervised pointwise object lo-calization and semantic segmentation. WILDCAT extends state-of-the-art Convolutional Neural Networks at three major levels: the use of Fully Convolutional Networks for maintaining spatial resolution, the explicit design in the network of local features related to different class modalities, and a new way to pool these features to provide a global image prediction required for weakly supervised training. Extensive experiments show that our model significantly out-performs the state-of-the-art methods.
Fichier principal
Vignette du fichier
0200.pdf (1.76 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01515640 , version 1 (29-08-2017)

Identifiants

Citer

Thibaut Durand, Taylor Mordan, Nicolas Thome, Matthieu Cord. WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), IEEE, Jul 2017, Honolulu, HI, United States. pp.5957-5966, ⟨10.1109/CVPR.2017.631⟩. ⟨hal-01515640⟩
974 Consultations
550 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More