S4Net: Single Stage Salient-Instance Segmentation

TL;DR

S4Net introduces a fast, single-stage salient instance segmentation network that produces high-quality instance-level segments by considering local and surrounding context, outperforming existing methods.

Contribution

The paper proposes a novel single-stage salient instance segmentation framework with a new segmentation branch that incorporates local and surrounding context for better instance differentiation.

Findings

Runs at 40 fps on 320x320 images

Outperforms other solutions on benchmark

Provides detailed analysis of design choices

Abstract

We consider an interesting problem-salient instance segmentation in this paper. Other than producing 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 320x320). We evaluate our approach on a publicly available benchmark and show that it outperforms other alternative solutions. We also provide a thorough analysis of the design choices to help readers better understand the functions of each part of our network. The source code can be found at \url{https://github.com/RuochenFan/S4Net}.