# Semantic Segmentation on NYU-v2 20-class (test)

Source: [Semantic Segmentation on NYU-v2 20-class (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-nyu-v2-20-class-test>)

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

Data updated: 2026-02-26T06:10:13.022Z

Evaluation of Semantic Segmentation performance on the 20-class subset of the NYU-v2 test split, reporting metrics such as Mean Intersection over Union (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) | NYU-v2 20-class (test) |
| Metric | mIoU |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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-nyu-v2-20-class-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mIoU | Result date | Report paper |
| --- | --- | --- | --- |
| 3D-to-2D distillation | 27.22 | Not recorded | 68fa69ae1e209131cea2358a |
| Cascade | 22.52 | Not recorded | 68fa69ae1e209131cea2358a |
| Multitask | 20.3 | Not recorded | 68fa69ae1e209131cea2358a |
| PSPNet-101 | 20.12 | Not recorded | 68fa69ae1e209131cea2358a |
| PSPNet-50 | 19.08 | Not recorded | 68fa69ae1e209131cea2358a |

### 3D-to-2D distillation

mIoU: 27.22. Result ID: 698dd1428b517eb43323ee31.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

[Implementation](<https://github.com/liuzhengzhe/3D-to-2D-Distillation-for-Indoor-Scene-Parsing>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training dataset":"ScanNet-v2"}. This record does not assert independent reproduction.

### Cascade

mIoU: 22.52. Result ID: 698dd1428b517eb43323ee30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ada1e209131cea2ac98.md>)

Recorded evaluation configuration: {"Training dataset":"ScanNet-v2"}. This record does not assert independent reproduction.

### Multitask

mIoU: 20.3. Result ID: 698dd1428b517eb43323ee2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

Recorded evaluation configuration: {"Training dataset":"ScanNet-v2"}. This record does not assert independent reproduction.

### PSPNet-101

mIoU: 20.12. Result ID: 698dd1428b517eb43323ee2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634b1e209131ce9fdc7e.md>)

[Implementation](<https://github.com/hszhao/PSPNet>)

Recorded evaluation configuration: {"Backbone":"ResNet-101","Training dataset":"ScanNet-v2"}. This record does not assert independent reproduction.

### PSPNet-50

mIoU: 19.08. Result ID: 698dd1428b517eb43323ee2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69ae1e209131cea2358a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa634b1e209131ce9fdc7e.md>)

[Implementation](<https://github.com/hszhao/PSPNet>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","Training dataset":"ScanNet-v2"}. This record does not assert independent reproduction.

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