Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks
While feedforward deep convolutional neural networks (CNNs) have been a great success in computer vision, it is important to note that the human visual cortex generally contains more feedback than feedforward connections. In this paper, we will briefly introduce the background of feedbacks in the human visual cortex, which motivates us to develop a computational feedback mechanism in deep neural networks. In addition to the feedforward inference in traditional neural networks, a feedback loop is introduced to infer the activation status of hidden layer neurons according to the “goal” of the network, e.g., high-level semantic labels. We analogize this mechanism as “Look and Think Twice.” The feedback networks help better visualize and understand how deep neural networks work, and capture visual attention on expected objects, even in images with cluttered background and multiple objects. Experiments on ImageNet dataset demonstrate its effectiveness in solving tasks such as image classification and object localization.
Text ReferenceChunshui Cao, Xianming Liu, Yi Yang, Yinan Yu, Jiang Wang, Zilei Wang, Yongzhen Huang, Liang Wang, Chang Huang, Wei Xu, Deva Ramanan, and Thomas S. Huang. Look and think twice: capturing top-down visual attention with feedback convolutional neural networks. In IEEE International Conference on Computer Vision. 2015.
author = "Cao, Chunshui and Liu, Xianming and Yang, Yi and Yu, Yinan and Wang, Jiang and Wang, Zilei and Huang, Yongzhen and Wang, Liang and Huang, Chang and Xu, Wei and Ramanan, Deva and Huang, Thomas S.",
booktitle = "IEEE International Conference on Computer Vision",
title = "Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks",
year = "2015"