Skip to main content

Research Repository

Advanced Search

PS-net: progressive selection network for salient object detection.

Ren, Jianyi; Wang, Zheng; Ren, Jinchang

Authors

Jianyi Ren

Zheng Wang

Jinchang Ren



Abstract

Low-level features contain abundant details and high-level features have rich semantic information. Integrating multi-scale features in an appropriate way is significant for salient object detection. However, direct concatenation or addition taken by most methods ignores the distinctions of contribution among multi-scale features. Besides, most salient object detection models fail to dynamically adjust receptive fields to fit objects of various sizes. To tackle these problems, we propose a Progressive Selection Network (PS-Net). Specifically, PS-Net dynamically extracts high-level features and encourages high-level features to guide low-level features to suppress the background response of the original features. We proposed a salient model PS-Net that selects features progressively at multiply levels. First, we propose a Pyramid Feature Dynamic Extraction module to dynamically select appropriate receptive fields to extract high-level features by Feature Dynamic Extraction modules step by step. Besides, a Self-Interaction Attention module is designed to extract detailed information for low-level features. Finally, we design a Scale Aware Fusion module to fuse these multiple features for adequate exploitation of high-level features to refine low-level features gradually. Compared with 19 start-of-the-art methods on 6 public benchmark datasets, the proposed method achieves remarkable performance in both quantitative and qualitative evaluation. We performed a lot of ablation studies, and more discussions to demonstrate the effectiveness and superiority of our proposed method. In this paper, we propose a PS-Net for effective salient object detection. Extensive experiments on 6 datasets validate that the proposed model outperforms 19 state-of-the-art methods under different evaluation metrics.

Citation

REN, J., WANG, Z. and REN, J. 2022. PS-net: progressive selection network for salient object detection. Cognitive computation [online], 14(2), pages 794-804. Available from: https://doi.org/10.1007/s12559-021-09952-4

Journal Article Type Article
Acceptance Date Sep 29, 2021
Online Publication Date Jan 16, 2022
Publication Date Mar 31, 2022
Deposit Date Jul 1, 2022
Publicly Available Date Jan 17, 2023
Journal Cognitive Computation
Print ISSN 1866-9956
Electronic ISSN 1866-9964
Publisher Springer
Peer Reviewed Peer Reviewed
Volume 14
Issue 2
Pages 794-804
DOI https://doi.org/10.1007/s12559-021-09952-4
Keywords Salient object detection; Attention mechanism; Multi-scale features
Public URL https://rgu-repository.worktribe.com/output/1584536