Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling
Metadata only
Date
2023-01Type
- Journal Article
ETH Bibliography
yes
Altmetrics
Abstract
Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed, all of which rely on the contour/edge information to improve detection performance. The edge labels are either put into the loss directly or used as extra supervision. The edge and body can also be learned separately and then fused afterward. Both methods either lead to high prediction errors near the edge or cannot be trained in an end-to-end manner. Another problem is that existing methods may fail to detect objects of various sizes due to the lack of efficient and effective feature fusion mechanisms. In this work, we propose to decompose the saliency detection task into two cascaded sub-tasks, i.e., detail modeling and body filling. Specifically, detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge. Then the body filling learns the body part that will be filled into the detail map to generate more accurate saliency map. To effectively fuse the features and handle objects at different scales, we have also proposed two novel multi-scale detail attention and body attention blocks for precise detail and body modeling. Experimental results show that our method achieves state-of-the-art performances on six public datasets. Show more
Publication status
publishedExternal links
Journal / series
ACM Transactions on Multimedia Computing, Communications and ApplicationsVolume
Pages / Article No.
Publisher
Association for Computing MachinerySubject
Salient object detection; Foreground segmentation; Visual saliencyMore
Show all metadata
ETH Bibliography
yes
Altmetrics