# Affinity Derivation and Graph Merge for Instance Segmentation

arXiv: https://arxiv.org/abs/1811.10870 · HTML: https://mlsanity.com/paper/1811.10870/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 25 of 25)

- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation](https://mlsanity.com/paper/2206.08948/) (2022)
- [SOTR: Segmenting Objects with Transformers](https://mlsanity.com/paper/2108.06747/) (2021)
- [Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity](https://mlsanity.com/paper/2204.06107/) (2022)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation](https://mlsanity.com/paper/2203.04074/) (2022)
- [Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition](https://mlsanity.com/paper/2204.04654/) (2022)
- [PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation](https://mlsanity.com/paper/2206.00468/) (2022)
- [Improving Video Instance Segmentation via Temporal Pyramid Routing](https://mlsanity.com/paper/2107.13155/) (2021)
- [iShape: A First Step Towards Irregular Shape Instance Segmentation](https://mlsanity.com/paper/2109.15068/) (2021)
- [SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation](https://mlsanity.com/paper/2203.13312/) (2022)
- [kMaX-DeepLab: k-means Mask Transformer](https://mlsanity.com/paper/2207.04044/) (2022)
- [Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach](https://mlsanity.com/paper/2106.03188/) (2021)
- [Recurrent Generic Contour-based Instance Segmentation with Progressive Learning](https://mlsanity.com/paper/2301.08898/) (2023)
- [Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision](https://mlsanity.com/paper/2303.05503/) (2023)
- [Real-time Instance Segmentation with Discriminative Orientation Maps](https://mlsanity.com/paper/2106.12204/) (2021)
- [Beyond mAP: Towards better evaluation of instance segmentation](https://mlsanity.com/paper/2207.01614/) (2022)
- [Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation](https://mlsanity.com/paper/2308.07592/) (2023)
- [Occlusion-Aware Instance Segmentation via BiLayer Network Architectures](https://mlsanity.com/paper/2208.04438/) (2022)
- [BoundarySqueeze: Image Segmentation as Boundary Squeezing](https://mlsanity.com/paper/2105.11668/) (2021)
- [Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation](https://mlsanity.com/paper/2211.06578/) (2022)
- [Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance](https://mlsanity.com/paper/2112.06454/) (2021)
- [Spatial-Temporal Deep Embedding for Vehicle Trajectory Reconstruction from High-Angle Video](https://mlsanity.com/paper/2209.08417/) (2022)
- [Deep Learning-Based 3D Instance and Semantic Segmentation: A Review](https://mlsanity.com/paper/2406.13308/) (2024)
- [SomaNet: Weakly Supervised Learning for Instance Soma Segmentation in 3D Electron Microscopy with Partial Annotations](https://mlsanity.com/paper/2609.23019/) (2026)

## Abstract (arXiv)

We present an instance segmentation scheme based on pixel affinity information, which is the relationship of two pixels belonging to a same instance. In our scheme, we use two neural networks with similar structure. One is to predict pixel level semantic score and the other is designed to derive pixel affinities. Regarding pixels as the vertexes and affinities as edges, we then propose a simple yet effective graph merge algorithm to cluster pixels into instances. Experimental results show that our scheme can generate fine-grained instance mask. With Cityscapes training data, the proposed scheme achieves 27.3 AP on test set.