# Segmentation Tracking on BDD100K (test)

Source: [Segmentation Tracking on BDD100K (test)](<https://www.sota2.com/research/sota/segmentation-tracking-on-bdd100k-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T06:11:00.009Z

Evaluation of Segmentation Tracking performance on the test split of the BDD100K dataset, reporting metrics such as mMOTSA, mMOTSP, and mIDF1.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Segmentation Tracking |
| Dataset (including any stated split) | BDD100K (test) |
| Metric | mMOTSA |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [mMOTSA](<https://www.sota2.com/research/sota/segmentation-tracking-on-bdd100k-test.md?metric=mMOTSA>): Higher is better; unit: PERCENT.

- [mMOTSP](<https://www.sota2.com/research/sota/segmentation-tracking-on-bdd100k-test.md?metric=mMOTSP>): Higher is better; unit: PERCENT.

- [mIDF1](<https://www.sota2.com/research/sota/segmentation-tracking-on-bdd100k-test.md?metric=mIDF1>): Higher is better; unit: PERCENT.

- [ID Swaps](<https://www.sota2.com/research/sota/segmentation-tracking-on-bdd100k-test.md?metric=ID%20Swaps>): Lower is better; unit: SCALAR.

## Recorded results

| Method | mMOTSA | Result date | Report paper |
| --- | --- | --- | --- |
| QDTrack | 30.8 | Not recorded | 68fa6ab61e209131cea29f88 |
| QDTrack | 24 | Not recorded | 68fa6ab61e209131cea29f88 |
| SORT | 12.8 | Not recorded | 68fa6ab61e209131cea29f88 |

### QDTrack

mMOTSA: 30.8. Result ID: 699acedf5698665ec45daf36.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ab61e209131cea29f88.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab61e209131cea29f88.md>)

[Implementation](<http://vis.xyz/pub/qdtrack>)

Recorded evaluation configuration: {"Pretrained":"ImageNet, BDD100K","Frozen":"Model pretrained from BDD100K tracking set, only finetune the mask head"}. This record does not assert independent reproduction.

### QDTrack

mMOTSA: 24. Result ID: 699acedf5698665ec45daf35.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ab61e209131cea29f88.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ab61e209131cea29f88.md>)

[Implementation](<http://vis.xyz/pub/qdtrack>)

Recorded evaluation configuration: {"Pretrained":"ImageNet, COCO, Cityscapes"}. This record does not assert independent reproduction.

### SORT

mMOTSA: 12.8. Result ID: 699acedf5698665ec45daf34.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ab61e209131cea29f88.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63851e209131ce9ff3be.md>)

[Implementation](<https://github.com/abewley/sort>)

Recorded evaluation configuration: {"Pretrained":"ImageNet, COCO, Cityscapes"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
