.png){kind=icon}
.png){kind=icon}
Return
Decomposition and Completion Network for Salient Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2021.3093380.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, fully convolutional networks (FCNs) have made great progress in the task of salient object detection and existing state-of-the-arts methods mainly focus on how to integrate edge information in deep aggregation models. In this paper, we propose a novel Decomposition and Completion Network (DCN), which integrates edge and skeleton as complementary information and models the integrity of salient objects in two stages. In the decomposition network, we propose a cross multi-branch decoder, which iteratively takes advantage of cross-task aggregation and cross-layer aggregation to integrate multi-level multi-task features and predict saliency, edge, and skeleton maps simultaneously. In the completion network, edge and skeleton maps are further utilized to fill flaws and suppress noises in saliency maps via hierarchical structure-aware feature learning and multi-scale feature completion. Through jointly learning with edge and skeleton information for localizing boundaries and interiors of salient objects respectively, the proposed network generates precise saliency maps with uniformly and completely segmented salient objects. Experiments conducted on five benchmark datasets demonstrate that the proposed model outperforms existing networks. Furthermore, we extend the proposed model to the task of RGB-D salient object detection, and it also achieves state-of-the-art performance. The code is available at https://github.com/wuzhe71/DCN.
Keywords:
Image edge detection
Skeleton
Task analysis
Object detection
Predictive models
Feature extraction
Decoding
Salient object detection
cross-task aggregation
cross-layer aggregation
saliency completion
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W