# A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation

arXiv: https://arxiv.org/abs/2106.10213 · HTML: https://mlsanity.com/paper/2106.10213/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 18 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Bottom-up Object Detection by Grouping Extreme and Center Points](https://mlsanity.com/paper/1901.08043/) (2019)
- [Semantic Instance Segmentation with a Discriminative Loss Function](https://mlsanity.com/paper/1708.02551/) (2017)
- [Deep Snake for Real-Time Instance Segmentation](https://mlsanity.com/paper/2001.01629/) (2020)
- [PolyTransform: Deep Polygon Transformer for Instance Segmentation](https://mlsanity.com/paper/1912.02801/) (2019)
- [SSAP: Single-Shot Instance Segmentation With Affinity Pyramid](https://mlsanity.com/paper/1909.01616/) (2019)
- [DirectPose: Direct End-to-End Multi-Person Pose Estimation](https://mlsanity.com/paper/1911.07451/) (2019)
- [Explicit Shape Encoding for Real-Time Instance Segmentation](https://mlsanity.com/paper/1908.04067/) (2019)
- [CenterMask: single shot instance segmentation with point representation](https://mlsanity.com/paper/2004.04446/) (2020)
- [DARNet: Deep Active Ray Network for Building Segmentation](https://mlsanity.com/paper/1905.05889/) (2019)
- [End to End Trainable Active Contours via Differentiable Rendering](https://mlsanity.com/paper/1912.00367/) (2019)
- [The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation](https://mlsanity.com/paper/2011.13241/) (2020)

## Built on by (most cited first, 3 of 3)

- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [Implicit Feature Refinement for Instance Segmentation](https://mlsanity.com/paper/2112.04709/) (2021)
- [UniInst: Unique Representation for End-to-End Instance Segmentation](https://mlsanity.com/paper/2205.12646/) (2022)

## Abstract (arXiv)

Boundary-based instance segmentation has drawn much attention since of its attractive efficiency. However, existing methods suffer from the difficulty in long-distance regression. In this paper, we propose a coarse-to-fine module to address the problem. Approximate boundary points are generated at the coarse stage and then features of these points are sampled and fed to a refined regressor for fine prediction. It is end-to-end trainable since differential sampling operation is well supported in the module. Furthermore, we design a holistic boundary-aware branch and introduce instance-agnostic supervision to assist regression. Equipped with ResNet-101, our approach achieves 31.7% mask AP on COCO dataset with single-scale training and testing, outperforming the baseline 1.3% mask AP with less than 1% additional parameters and GFLOPs. Experiments also show that our proposed method achieves competitive performance compared to existing boundary-based methods with a lightweight design and a simple pipeline.