# Amodal Instance Segmentation on OccHuman (val)

Source: [Amodal Instance Segmentation on OccHuman (val)](<https://www.sota2.com/research/sota/amodal-instance-segmentation-on-occhuman-val>)

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

Data updated: 2026-02-26T05:22:52.559Z

Evaluation of Amodal Instance Segmentation performance on the validation split of the OccHuman dataset, reporting AP, APM, and APH 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 | Amodal Instance Segmentation |
| Dataset (including any stated split) | OccHuman (val) |
| Metric | AP |
| 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

- [AP](<https://www.sota2.com/research/sota/amodal-instance-segmentation-on-occhuman-val.md?metric=AP>): Higher is better; unit: PERCENT.

- [APM](<https://www.sota2.com/research/sota/amodal-instance-segmentation-on-occhuman-val.md?metric=APM>): Higher is better; unit: PERCENT.

- [APH](<https://www.sota2.com/research/sota/amodal-instance-segmentation-on-occhuman-val.md?metric=APH>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AP | Result date | Report paper |
| --- | --- | --- | --- |
| Crowd-SAM | 31.4 | Not recorded | 68fa74321e209131cea605e3 |
| Pose2Seg | 22.2 | Not recorded | 68fa74321e209131cea605e3 |
| Mask R-CNN | 16.3 | Not recorded | 68fa74321e209131cea605e3 |

### Crowd-SAM

AP: 31.4. Result ID: 699341de3a6c31484914c08d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605e3.md>)

[Implementation](<https://github.com/FelixCaae/CrowdSAM>)

Recorded evaluation configuration: {"Backbone":"VIT-L \[7\]"}. This record does not assert independent reproduction.

### Pose2Seg

AP: 22.2. Result ID: 699341de3a6c31484914c08c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d467.md>)

[Implementation](<https://github.com/liruilong940607/Pose2Seg>)

Recorded evaluation configuration: {"Backbone":"ResNet50-FPN \[14\]"}. This record does not assert independent reproduction.

### Mask R-CNN

AP: 16.3. Result ID: 699341de3a6c31484914c08b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa74321e209131cea605e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f21e209131cea01b22.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"Backbone":"ResNet50-FPN \[14\]"}. This record does not assert independent reproduction.

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