# Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation

arXiv: https://arxiv.org/abs/2605.31094 · HTML: https://mlsanity.com/paper/2605.31094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 13 of 13)

- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [Simultaneous Detection and Segmentation](https://mlsanity.com/paper/1407.1808/) (2014)
- [Part-aware Panoptic Segmentation](https://mlsanity.com/paper/2106.06351/) (2021)
- [blob loss: instance imbalance aware loss functions for semantic segmentation](https://mlsanity.com/paper/2205.08209/) (2022)
- [Analysis of the MICCAI Brain Tumor Segmentation -- Metastases (BraTS-METS) 2025 Lighthouse Challenge: Brain Metastasis Segmentation on Pre- and Post-treatment MRI](https://mlsanity.com/paper/2504.12527/) (2025)
- [Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps](https://mlsanity.com/paper/2312.02608/) (2023)
- [SortedAP: Rethinking evaluation metrics for instance segmentation](https://mlsanity.com/paper/2309.04887/) (2023)
- [Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks](https://mlsanity.com/paper/2410.18684/) (2024)

## Built on by (most cited first, 1 of 1)

- [Toward Open-World Video Segmentation over Long Horizons](https://mlsanity.com/paper/2606.15632/) (2026)

## Abstract (arXiv)

The Panoptic Quality (PQ) metric is the standard for jointly evaluating instance and semantic segmentation. However, its original definition relies on a One-to-One matching between predicted and ground truth segments, which is only straightforward when the IoU threshold exceeds 0.5. Below 0.5, multiple matching strategies emerge in a poorly explored problem space. We systematically elucidate this space by recasting segment matching as a constrained bipartite assignment problem. Independently bounding the prediction- and ground-truth-side degrees yields four matching strategies: One-to-One, Many-to-One, One-to-Many, and Many-to-Many. We show that the first three are well-defined within the PQ framework, while Many-to-Many falls outside it. These strategies become relevant when instances are fragmented, adjacent objects are difficult to delineate, or annotations are noisy. Central to our framework is a vertex-based accounting of TP, FN, and FP, anchored to ground truth and predicted segments rather than to matching edges. We further show that the framework extends naturally to part-aware panoptic segmentation, and we explore part-aware evaluation on biomedical data. Across configurable case studies we report how different combinations of thresholds and matching strategies behave in practice. We release a unified open-source package built on Panoptica. It exposes Voronoi-based region-wise analysis, part-aware evaluation, and Area Under Threshold Curve computations as configurable options.