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

被引：143

作者：

Durand, Thibaut ^{[1
]}

Mordan, Taylor ^{[1
,2
]}

Thome, Nicolas ^{[3
]}

Cord, Matthieu ^{[1
]}

机构：

[1] UPMC Univ Paris 06, Sorbonne Univ, CNRS, LIP6,UMR 7606, 4 Pl Jussieu, F-75005 Paris, France

[2] Thales Optron SAS, 2 Ave Gay Lussac, F-78990 Elancourt, France

[3] CEDRIC Conservatoire Natl Arts & Metiers, 292 Rue St Martin, F-75003 Paris, France

来源：

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) | 2017年

关键词：

D O I：

10.1109/CVPR.2017.631

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 localization 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 outperforms the state-of-the-art methods.

引用

页码：5957 / 5966

页数：10