# Semantic Segmentation on PASCAL VOC blender 1/4 partition 2012 (val)

Source: [Semantic Segmentation on PASCAL VOC blender 1/4 partition 2012 (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-pascal-voc-blender-1-4-partition-2012-val>)

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

Data updated: 2026-02-26T06:10:22.391Z

Evaluation of Semantic Segmentation performance on the specific 1/4 partition of the validation split of the PASCAL VOC 2012 dataset rendered using Blender assets, reporting 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) | PASCAL VOC blender 1/4 partition 2012 (val) |
| 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/semantic-segmentation-on-pascal-voc-blender-1-4-partition-2012-val.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| Dual Teacher | 81.03 | Not recorded | 68fa71041e209131cea4e95a |
| PCR | 80.78 | Not recorded | 68fa71041e209131cea4e95a |
| GTA-Seg | 80.57 | Not recorded | 68fa71041e209131cea4e95a |
| U2PL | 79.3 | Not recorded | 68fa71041e209131cea4e95a |
| AEL | 78.06 | Not recorded | 68fa71041e209131cea4e95a |
| CPS | 77.68 | Not recorded | 68fa71041e209131cea4e95a |
| Supervised-only | 75.8 | Not recorded | 68fa71041e209131cea4e95a |
| MT | 73.02 | Not recorded | 68fa71041e209131cea4e95a |

### Dual Teacher

mIoU: 81.03. Result ID: 699189993a6c31484908ce32.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Implementation](<https://github.com/naver-ai/dual-teacher>)

Recorded evaluation configuration: {"#Params":"62.6M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### PCR

mIoU: 80.78. Result ID: 699189993a6c31484908ce31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6da41e209131cea3b17f.md>)

[Implementation](<https://github.com/HeimingX/semi_seg_proto>)

Recorded evaluation configuration: {"#Params":"64.5M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### GTA-Seg

mIoU: 80.57. Result ID: 699189993a6c31484908ce30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e641e209131cea3fa7c.md>)

[Implementation](<https://github.com/Jin-Ying/GTA-Seg>)

Recorded evaluation configuration: {"#Params":"127.1M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### U2PL

mIoU: 79.3. Result ID: 699189993a6c31484908ce2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bff1e209131cea318a4.md>)

[Implementation](<https://haochen-wang409.github.io/U2PL>)

Recorded evaluation configuration: {"#Params":"64.5M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### AEL

mIoU: 78.06. Result ID: 699189993a6c31484908ce2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aff1e209131cea2ba14.md>)

[Implementation](<https://github.com/hzhupku/SemiSeg-AEL>)

Recorded evaluation configuration: {"#Params":"62.6M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### CPS

mIoU: 77.68. Result ID: 699189993a6c31484908ce2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a231e209131cea26482.md>)

[Implementation](<https://git.io/CPS>)

Recorded evaluation configuration: {"#Params":"125.2M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### Supervised-only

mIoU: 75.8. Result ID: 699189993a6c31484908ce2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

Recorded evaluation configuration: {"#Params":"62.6M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

### MT

mIoU: 73.02. Result ID: 699189993a6c31484908ce2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa71041e209131cea4e95a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64481e209131cea03b45.md>)

[Implementation](<https://github.com/CuriousAI/mean-teacher>)

Recorded evaluation configuration: {"#Params":"62.6M","Backbone":"ResNet-101","Architecture":"DeepLabv3+","Training Resolution":"513x513"}. This record does not assert independent reproduction.

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