Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aw...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings / IEEE International Conference on Computer Vision pp. 7263 - 7272
Main Authors: Wu, Zhe, Su, Li, Huang, Qingming
Format: Conference Proceeding
Language:English
Published: IEEE 01.10.2019
Subjects:
Computational modeling
Feature extraction
Image edge detection
Image segmentation
Object detection
Silicon
Task analysis
ISSN:2380-7504
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00736