# Deep Affinity Net: Instance Segmentation via Affinity

arXiv: https://arxiv.org/abs/2003.06849 · HTML: https://mlsanity.com/paper/2003.06849/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2020.

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

- [UltraSR: Spatial Encoding is a Missing Key for Implicit Image Function-based Arbitrary-Scale Super-Resolution](https://mlsanity.com/paper/2103.12716/) (2021)
- [Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision](https://mlsanity.com/paper/2303.05503/) (2023)
- [MSN: Efficient Online Mask Selection Network for Video Instance Segmentation](https://mlsanity.com/paper/2106.10452/) (2021)

## Abstract (arXiv)

Most of the modern instance segmentation approaches fall into two categories: region-based approaches in which object bounding boxes are detected first and later used in cropping and segmenting instances; and keypoint-based approaches in which individual instances are represented by a set of keypoints followed by a dense pixel clustering around those keypoints. Despite the maturity of these two paradigms, we would like to report an alternative affinity-based paradigm where instances are segmented based on densely predicted affinities and graph partitioning algorithms. Such affinity-based approaches indicate that high-level graph features other than regions or keypoints can be directly applied in the instance segmentation task. In this work, we propose Deep Affinity Net, an effective affinity-based approach accompanied with a new graph partitioning algorithm Cascade-GAEC. Without bells and whistles, our end-to-end model results in 32.4% AP on Cityscapes val and 27.5% AP on test. It achieves the best single-shot result as well as the fastest running time among all affinity-based models. It also outperforms the region-based method Mask R-CNN.