# Semantic Segmentation on GWFSS 1.0 (test)

Source: [Semantic Segmentation on GWFSS 1.0 (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-gwfss-1-0-test>)

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

Data updated: 2026-02-26T06:10:44.917Z

Evaluation of Semantic Segmentation performance on the test split of the GWFSS 1.0 dataset, measured using mIoU.

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 | Semantic Segmentation |
| Dataset (including any stated split) | GWFSS 1.0 (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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/semantic-segmentation-on-gwfss-1-0-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| DepthCropSeg++ | 93.11 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| DepthCropSeg++ | 92.88 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| DepthCropSeg++ | 92.86 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| Fully Supervised | 92.75 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| Semi-supervised baseline | 92.36 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| Proposed Self-Training Framework | 70.99 | Not recorded | 6940e791456146936284f74d |
| GWFSS Top-Solution | 69.5 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| HQ-SAM | 44.54 | Not recorded | 69705d6de25ad2fa9d1ecf64 |
| SAM | 32.8 | Not recorded | 69705d6de25ad2fa9d1ecf64 |

### DepthCropSeg++

mIoU: 93.11. Result ID: 6997af185698665ec405401c.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: {"Depth-based Pseudo-masks":true,"Two-stage Self-training":true,"FADE Upsampling":true}. This record does not assert independent reproduction.

### DepthCropSeg++

mIoU: 92.88. Result ID: 6997af185698665ec405401b.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: {"Depth-based Pseudo-masks":true,"Two-stage Self-training":true,"FADE Upsampling":false}. This record does not assert independent reproduction.

### DepthCropSeg++

mIoU: 92.86. Result ID: 6997af185698665ec405401a.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: {"Depth-based Pseudo-masks":true,"Two-stage Self-training":false,"FADE Upsampling":false}. This record does not assert independent reproduction.

### Fully Supervised

mIoU: 92.75. Result ID: 6997af185698665ec4054020.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Semi-supervised baseline

mIoU: 92.36. Result ID: 6997af185698665ec4054019.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: {"Depth-based Pseudo-masks":false,"Two-stage Self-training":false,"FADE Upsampling":false}. This record does not assert independent reproduction.

### Proposed Self-Training Framework

mIoU: 70.99. Result ID: 699881685698665ec4e2a15d.

[Reporting paper](<https://www.sota2.com/research/paper/6940e791456146936284f74d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e791456146936284f74d.md>)

Recorded evaluation configuration: {"Backbone":"SegFormer","Training Strategy":"Two-Stage Hybrid (Iterative Teacher-Student Loop)","Cross-validation":"10-fold","Model Ensembling":"true","Test-Time Augmentation (TTA)":"true"}. This record does not assert independent reproduction.

### GWFSS Top-Solution

mIoU: 69.5. Result ID: 6997af185698665ec405401f.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7adf1e209131cea859d8.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HQ-SAM

mIoU: 44.54. Result ID: 6997af185698665ec405401e.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SAM

mIoU: 32.8. Result ID: 6997af185698665ec405401d.

[Reporting paper](<https://www.sota2.com/research/paper/69705d6de25ad2fa9d1ecf64.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f0a1e209131cea437f2.md>)

[Implementation](<https://segment-anything.com/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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