---

First published: 2017/11/21 (7 years ago)
Abstract: In this paper, we consider an interesting vision problem---salient instance segmentation. Other than producing approximate bounding boxes, our network also outputs high-quality instance-level segments. 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 its surrounding context, enabling us to distinguish the instances in the same scope even with obstruction. Our network is end-to-end trainable and runs at a fast speed (40 fps when processing an image with resolution $320 \times 320$). We evaluate our approach on a public available benchmark and show that it outperforms other alternative solutions. In addition, we also provide a thorough analysis of the design choices to help readers better understand the functions of each part of our network. To facilitate the development of this area, our code will be available at \url{https://github.com/RuochenFan/S4Net}.