Stacked Cross Refinement Network for Edge-Aware Salient Object Detection

ICCV 2019  ·  Zhe Wu, Li Su, Qingming Huang ·

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 read more

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
RGB Salient Object Detection SOC SCRN S-Measure 0.838 # 4
mean E-Measure 0.859 # 4
Average MAE 0.099 # 4