# Scene Classification on NYU v2 enriched (test)

Source: [Scene Classification on NYU v2 enriched (test)](<https://www.sota2.com/research/sota/scene-classification-on-nyu-v2-enriched-test>)

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

Data updated: 2026-02-26T05:37:32.288Z

Evaluation of Scene Classification performance on the test split of the enriched NYU v2 dataset, typically measured using Balanced Accuracy (bAcc).

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 | Scene Classification |
| Dataset (including any stated split) | NYU v2 enriched (test) |
| Metric | Balanced Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Balanced Accuracy](<https://www.sota2.com/research/sota/scene-classification-on-nyu-v2-enriched-test.md?metric=Balanced%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Balanced Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| EMSANet | 77.41 | Not recorded | 68fa70b21e209131cea4ca72 |
| EMSANet | 76.46 | Not recorded | 68fa70b21e209131cea4ca72 |
| EMSANet | 75.25 | Not recorded | 68fa70b21e209131cea4ca72 |
| EMSANet | 70.88 | Not recorded | 68fa70b21e209131cea4ca72 |
| EfficientNet | 70.83 | Not recorded | 68fa70b21e209131cea4ca72 |
| Mod. ResNet34 | 70.25 | Not recorded | 68fa70b21e209131cea4ca72 |
| MobileNetV2 | 69.2 | Not recorded | 68fa70b21e209131cea4ca72 |

### EMSANet

Balanced Accuracy: 77.41. Result ID: 699154223a6c3148490759d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Implementation](<https://github.com/TUI-NICR/EMSANet>)

Recorded evaluation configuration: {"Backbone":"2xR101-Nbt1d","Modality":"RGB-D"}. This record does not assert independent reproduction.

### EMSANet

Balanced Accuracy: 76.46. Result ID: 699154223a6c3148490759d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Implementation](<https://github.com/TUI-NICR/EMSANet>)

Recorded evaluation configuration: {"Backbone":"2xR34-Nbt1d","Modality":"RGB-D"}. This record does not assert independent reproduction.

### EMSANet

Balanced Accuracy: 75.25. Result ID: 699154223a6c3148490759d4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Implementation](<https://github.com/TUI-NICR/EMSANet>)

Recorded evaluation configuration: {"Backbone":"2xR34-Nbt1d","Modality":"RGB-D","Pre-training":"Hypersim"}. This record does not assert independent reproduction.

### EMSANet

Balanced Accuracy: 70.88. Result ID: 699154223a6c3148490759d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Implementation](<https://github.com/TUI-NICR/EMSANet>)

Recorded evaluation configuration: {"Backbone":"R34-Nbt1d","Modality":"RGB"}. This record does not assert independent reproduction.

### EfficientNet

Balanced Accuracy: 70.83. Result ID: 699154223a6c3148490759cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684f1e209131cea1b521.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet>)

Recorded evaluation configuration: {"Backbone":"B0","Modality":"RGB","Enriched NYUv2":true,"Evaluation Protocol":"ten-crop"}. This record does not assert independent reproduction.

### Mod. ResNet34

Balanced Accuracy: 70.25. Result ID: 699154223a6c3148490759d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Implementation](<https://github.com/TUI-NICR/EMSANet>)

Recorded evaluation configuration: {"Backbone":"R34-Nbt1d","Modality":"RGB","Evaluation Protocol":"ten-crop"}. This record does not assert independent reproduction.

### MobileNetV2

Balanced Accuracy: 69.2. Result ID: 699154223a6c3148490759ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b21e209131cea4ca72.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65811e209131cea0a9a1.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/research/slim/nets/mobilenet>)

Recorded evaluation configuration: {"Backbone":"alpha=1","Modality":"RGB","Enriched NYUv2":true,"Evaluation Protocol":"ten-crop"}. This record does not assert independent reproduction.

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