Lightning-AI / Lightning-AI/torchmetrics

Robust instance segmentation metrics

Open
#3,163 8 comments 0 reactions 1 assignee View on GitHub

@hciays is already working on this.

Since Jul 11, 2025.

enhancement New metric
Dominant language
Python
Stars
2.5k
Forks
526
Avg merge
6d 11h
Merged PRs (30d)
5

Description

## 🚀 SortedAP and Aggregated Jacard Index metrics

### Motivation

Instance segmentation is a critical task in biomedical image analysis, where accurate evaluation of predicted object masks is essential. While TorchMetrics currently supports common metrics such as IoU, Dice, PQ, mPQ and mAP, which often are not recommended for biomedical instance segmentation, there is no implementation for robust metrics such as SortedAP and AJI.

### Pitch
Implement these metrics and offer additional options

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.