# Amodal Segmentation on Chewing Gum (test)

Source: [Amodal Segmentation on Chewing Gum (test)](<https://www.sota2.com/research/sota/amodal-segmentation-on-chewing-gum-test>)

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

Data updated: 2026-02-26T06:10:56.320Z

Evaluation of Amodal Segmentation performance on the test split of the Chewing Gum dataset, measured using Mean-IoU for both full and occluded regions.

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 Segmentation |
| Dataset (including any stated split) | Chewing Gum (test) |
| Metric | mIoU (Full) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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 (Full)](<https://www.sota2.com/research/sota/amodal-segmentation-on-chewing-gum-test.md?metric=mIoU%20(Full)>): Higher is better; unit: PERCENT.

- [mIoU (Occluded)](<https://www.sota2.com/research/sota/amodal-segmentation-on-chewing-gum-test.md?metric=mIoU%20(Occluded)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU (Full) | Result date | Report paper |
| --- | --- | --- | --- |
| SaVos | 97.46 | Not recorded | 68fa6db81e209131cea3b8b7 |
| Self-Deocclusion | 96.24 | Not recorded | 68fa6db81e209131cea3b8b7 |
| U-Net | 96.13 | Not recorded | 68fa6db81e209131cea3b8b7 |
| Convex | 92.64 | Not recorded | 68fa6db81e209131cea3b8b7 |

### SaVos

mIoU (Full): 97.46. Result ID: 698fd5913a6c314849fc314b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6db81e209131cea3b8b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6db81e209131cea3b8b7.md>)

Recorded evaluation configuration: {"Supervised":false}. This record does not assert independent reproduction.

### Self-Deocclusion

mIoU (Full): 96.24. Result ID: 698fd5913a6c314849fc314a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6db81e209131cea3b8b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67511e209131cea1560f.md>)

Recorded evaluation configuration: {"Supervised":false}. This record does not assert independent reproduction.

### U-Net

mIoU (Full): 96.13. Result ID: 698fd5913a6c314849fc314c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6db81e209131cea3b8b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

Recorded evaluation configuration: {"Supervised":true,"Role":"Supervised Oracle"}. This record does not assert independent reproduction.

### Convex

mIoU (Full): 92.64. Result ID: 698fd5913a6c314849fc3149.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6db81e209131cea3b8b7.md>)

Recorded evaluation configuration: {"Supervised":false}. This record does not assert independent reproduction.

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