Lightning-AI / Lightning-AI/torchmetrics
Robust instance segmentation metrics
Open
@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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.