Salient Object Detection via fast R-CNN and Low-level Cues

Abstract

Recent advances in salient object detection have exploited the deep Convolutional Neural Network (CNN) to represent high-level semantic, however, due to the presence of convolutional and pooling layers, it is difficult for CNN to generate saliency map with sharp boundaries. In this paper, we propose multi-scale mask-based Fast R-CNN framework which generate saliency score of each region. Since the regions are segmented using edge-preserved methods, the results are naturally with sharp boundaries. To consider context information, we also propose low-level contrast and backgroundness prior which are complementary with high-level semantic. Finally, an edge-based propagation method which takes advantages of edge information is proposed to refine the saliency map. Experiments on three benchmark datasets demonstrate that the proposed method outperforms previous methods and achieves state-of-the-art performance.

Paper

ICIP 2016 Oral Presentation (PDF)
@inproceedings{wang2016salient, 
author={Wang, Xiang and Ma, Huimin and Chen, Xiaozhi}, 
booktitle={2016 IEEE International Conference on Image Processing (ICIP)}, 
title={Salient object detection via fast R-CNN and low-level cues}, 
year={2016}, 
pages={1042-1046}, 
doi={10.1109/ICIP.2016.7532516}, 
}

Results

We test our method on 6 typical benchmark RGB datasets: ECSSD, DUT-OMRON, JuddDB, SED2, THUR15K and Pascal-S.

Dummy Image

Comparison with state-of-the-art methods on three benchmark datasets. The first row shows the PR curves and the second row shows the F-measure.

Code

  • will be released