Image Saliency Prediction in Transformed Domain: A Deep Complex Neural Network Method

Authors

  • Lai Jiang Beihang University
  • Zhe Wang Beihang University
  • Mai Xu Beihang University
  • Zulin Wang Beihang University

DOI:

https://doi.org/10.1609/aaai.v33i01.33018521

Abstract

The transformed domain fearures of images show effectiveness in distinguishing salient and non-salient regions. In this paper, we propose a novel deep complex neural network, named SalDCNN, to predict image saliency by learning features in both pixel and transformed domains. Before proposing Sal-DCNN, we analyze the saliency cues encoded in discrete Fourier transform (DFT) domain. Consequently, we have the following findings: 1) the phase spectrum encodes most saliency cues; 2) a certain pattern of the amplitude spectrum is important for saliency prediction; 3) the transformed domain spectrum is robust to noise and down-sampling for saliency prediction. According to these findings, we develop the structure of SalDCNN, including two main stages: the complex dense encoder and three-stream multi-domain decoder. Given the new SalDCNN structure, the saliency maps can be predicted under the supervision of ground-truth fixation maps in both pixel and transformed domains. Finally, the experimental results show that our Sal-DCNN method outperforms other 8 state-of-theart methods for image saliency prediction on 3 databases.

Downloads

Published

2019-07-17

How to Cite

Jiang, L., Wang, Z., Xu, M., & Wang, Z. (2019). Image Saliency Prediction in Transformed Domain: A Deep Complex Neural Network Method. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 8521-8528. https://doi.org/10.1609/aaai.v33i01.33018521

Issue

Section

AAAI Technical Track: Vision