Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection

Authors

  • Chunshui Cao University of Science and Technology of China
  • Yongzhen Huang Institute of Automation, Chinese Academy of Sciences
  • Zilei Wang University of Science and Technology of China
  • Liang Wang Institute of Automation, Chinese Academy of Sciences
  • Ninglong Xu Shanghai Institutes for Biological Sciences, Chinese Academy of Sciences, Institute of Neuroscience
  • Tieniu Tan Institute of Automation, Chinese Academy of Sciences

DOI:

https://doi.org/10.1609/aaai.v32i1.12238

Keywords:

lateral inhibition, convolutional neural network, top-down attention, saliency detection

Abstract

Lateral inhibition in top-down feedback is widely existing in visual neurobiology, but such an important mechanism has not be well explored yet in computer vision. In our recent research, we find that modeling lateral inhibition in convolutional neural network (LICNN) is very useful for visual attention and saliency detection. In this paper, we propose to formulate lateral inhibition inspired by the related studies from neurobiology, and embed it into the top-down gradient computation of a general CNN for classification, i.e. only category-level information is used. After this operation (only conducted once), the network has the ability to generate accurate category-specific attention maps. Further, we apply LICNN for weakly-supervised salient object detection.Extensive experimental studies on a set of databases, e.g., ECSSD, HKU-IS, PASCAL-S and DUT-OMRON, demonstrate the great advantage of LICNN which achieves the state-of-the-art performance. It is especially impressive that LICNN with only category-level supervised information even outperforms some recent methods with segmentation-level supervised learning.

Downloads

Published

2018-04-27

How to Cite

Cao, C., Huang, Y., Wang, Z., Wang, L., Xu, N., & Tan, T. (2018). Lateral Inhibition-Inspired Convolutional Neural Network for Visual Attention and Saliency Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). https://doi.org/10.1609/aaai.v32i1.12238