Harnessing noisy Web images for deep representation - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Article Dans Une Revue Computer Vision and Image Understanding Année : 2017

Harnessing noisy Web images for deep representation

Résumé

The keep-growing content of Web images is probably the next important data source to scale up deep neural networks which recently surpass human in image classification tasks. The fact that deep networks are hungry for labelled data limits themselves from extracting valuable information of Web images which are abundant and cheap. There have been efforts to train neural networks such as autoencoders with respect to either unsupervised or semi-supervised settings. Nonetheless they are less performant than supervised methods partly because the loss function used in unsupervised methods, for instance Euclidean loss, failed to guide the network to learn discriminative features and ignore unnecessary details. We instead train convolutional networks in a supervised setting but use weakly labelled data which are large amounts of unannotated Web images downloaded from Flickr and Bing. Our experiments are conducted at several data scales, with different choices of network architecture, and alternating between different data preprocessing techniques. The effectiveness of our approach is shown by the good generalization of the learned representations with new six public datasets.
Fichier non déposé

Dates et versions

cea-01756775 , version 1 (03-04-2018)

Identifiants

Citer

Phong D. Vo, Alexandru Ginsca, Hervé Le Borgne, Adrian Popescu. Harnessing noisy Web images for deep representation. Computer Vision and Image Understanding, 2017, 164, pp.68 - 81. ⟨10.1016/j.cviu.2017.01.009⟩. ⟨cea-01756775⟩
101 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More