Recurrently Aggregating Deep Features for Salient Object Detection

Authors

  • Xiaowei Hu The Chinese University of Hong Kong
  • Lei Zhu The Hong Kong Polytechnic University
  • Jing Qin The Hong Kong Polytechnic University
  • Chi-Wing Fu The Chinese University of Hong Kong; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
  • Pheng-Ann Heng The Chinese University of Hong Kong; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences

Keywords:

Salient Object, Deep Features, Saliency Detection

Abstract

Salient object detection is a fundamental yet challenging problem in computer vision, aiming to highlight the most visually distinctive objects or regions in an image. Recent works benefit from the development of fully convolutional neural networks (FCNs) and achieve great success by integrating features from multiple layers of FCNs. However, the integrated features tend to include non-salient regions (due to low level features of the FCN) or lost details of salient objects (due to high level features of the FCN) when producing the saliency maps. In this paper, we develop a novel deep saliency network equipped with recurrently aggregated deep features (RADF) to more accurately detect salient objects from an image by fully exploiting the complementary saliency information captured in different layers. The RADF utilizes the multi-level features integrated from different layers of a FCN to recurrently refine the features at each layer, suppressing the non-salient noise at low-level of the FCN and increasing more salient details into features at high layers. We perform experiments to evaluate the effectiveness of the proposed network on 5 famous saliency detection benchmarks and compare it with 15 state-of-the-art methods. Our method ranks first in 4 of the 5 datasets and second in the left dataset.

Downloads

Published

2018-04-27

How to Cite

Hu, X., Zhu, L., Qin, J., Fu, C.-W., & Heng, P.-A. (2018). Recurrently Aggregating Deep Features for Salient Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12298