Top-down Neural Attention by Excitation Backprop
arXiv:1608.00507
Abstract
We aim to model the top-down attention of a Convolutional Neural Network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process. Furthermore, we introduce the concept of contrastive attention to make the top-down attention maps more discriminative. In experiments, we demonstrate the accuracy and generalizability of our method in weakly supervised localization tasks on the MS COCO, PASCAL VOC07 and ImageNet datasets. The usefulness of our method is further validated in the text-to-region association task. On the Flickr30k Entities dataset, we achieve promising performance in phrase localization by leveraging the top-down attention of a CNN model that has been trained on weakly labeled web images.
arXiv commentA shorter version of this paper is accepted at ECCV, 2016 (oral)
References in corpus (5)
- Striving for Simplicity: The All Convolutional Net
- Understanding Neural Networks Through Deep Visualization
- Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
- Recurrent Convolutional Neural Networks for Scene Parsing
- Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models