In this paper, we consider salient instance segmentation. As well as producing bounding boxes, our network also outputs high-quality instance-level segments as initial selections to indicate the regions of interest. Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch. Our new branch regards not only local context inside each detection window but also the surrounding context, enabling us to distinguish instances in the same scope even with partial occlusion. Our network is end-to-end trainable and is fast (running at 40 fps for images with resolution
Publications
- Article type
- Year
- Co-author
Article type
Year
Open Access
Research Article
Issue
Computational Visual Media 2020, 6(2): 191-204
Published: 10 June 2020
Downloads:39
Total 1