作者
Thibaut Durand, Taylor Mordan, Nicolas Thome, Matthieu Cord
发表日期
2017
研讨会论文
Proceedings of the IEEE conference on computer vision and pattern recognition
页码范围
642-651
简介
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 object localization and semantic segmentation. WILDCAT extends state-of-the-art Convolutional Neural Networks at three main 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 state-of-the-art methods.
引用总数
20172018201920202021202220232024959757160585223
学术搜索中的文章