# Human Parts Segmentation on PASCAL Human Parts ID Clean (test)

Source: [Human Parts Segmentation on PASCAL Human Parts ID Clean (test)](<https://www.sota2.com/research/sota/human-parts-segmentation-on-pascal-human-parts-id-clean-test>)

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

Data updated: 2026-02-26T06:10:22.604Z

Evaluation of Human Parts Segmentation performance on the test split of the PASCAL Human Parts ID Clean dataset, reporting mIoU and ID Δ metrics.

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 | Human Parts Segmentation |
| Dataset (including any stated split) | PASCAL Human Parts ID Clean (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [mIoU](<https://www.sota2.com/research/sota/human-parts-segmentation-on-pascal-human-parts-id-clean-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

- [ID Δ (%)](<https://www.sota2.com/research/sota/human-parts-segmentation-on-pascal-human-parts-id-clean-test.md?metric=ID%20%CE%94%20(%25)>): Lower is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| FTP | 65.5 | Not recorded | 68fa71051e209131cea4ea0c |
| LLRD | 64.37 | Not recorded | 68fa71051e209131cea4ea0c |
| TPGM | 63.29 | Not recorded | 68fa71051e209131cea4ea0c |
| MARS-SP | 62.92 | Not recorded | 68fa71051e209131cea4ea0c |
| Vanilla FT | 62.61 | Not recorded | 68fa71051e209131cea4ea0c |
| L2-SP | 62.26 | Not recorded | 68fa71051e209131cea4ea0c |
| Adapter | 60.84 | Not recorded | 68fa71051e209131cea4ea0c |
| BitFit | 59.06 | Not recorded | 68fa71051e209131cea4ea0c |

### FTP

mIoU: 65.5. Result ID: 69918b233a6c31484908dd3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Implementation](<https://github.com/GT-RIPL/FTP.git>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.397}. This record does not assert independent reproduction.

### LLRD

mIoU: 64.37. Result ID: 69918b233a6c31484908dd3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea2275e.md>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.278}. This record does not assert independent reproduction.

### TPGM

mIoU: 63.29. Result ID: 69918b233a6c31484908dd3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428cb.md>)

[Implementation](<https://github.com/PotatoTian/TPGM>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.602}. This record does not assert independent reproduction.

### MARS-SP

mIoU: 62.92. Result ID: 69918b233a6c31484908dd3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69181e209131cea20288.md>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.308}. This record does not assert independent reproduction.

### Vanilla FT

mIoU: 62.61. Result ID: 69918b233a6c31484908dd37.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.28}. This record does not assert independent reproduction.

### L2-SP

mIoU: 62.26. Result ID: 69918b233a6c31484908dd3a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64671e209131cea046e0.md>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.336}. This record does not assert independent reproduction.

### Adapter

mIoU: 60.84. Result ID: 69918b233a6c31484908dd38.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65e31e209131cea0d324.md>)

[Implementation](<https://github.com/google-research/adapter-bert>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.221}. This record does not assert independent reproduction.

### BitFit

mIoU: 59.06. Result ID: 69918b233a6c31484908dd39.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71051e209131cea4ea0c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d5a1e209131cea39632.md>)

[Implementation](<https://www.github.com/benzakenelad/BitFit>)

Recorded evaluation configuration: {"Backbone":"Swin-Tiny","Pre-trained":"ImageNet21K","Time (s/it)":0.235}. This record does not assert independent reproduction.

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