# Depth Image Classification on SUN RGB-D (val)

Source: [Depth Image Classification on SUN RGB-D (val)](<https://www.sota2.com/research/sota/depth-image-classification-on-sun-rgb-d-val>)

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

Data updated: 2026-02-26T06:07:12.495Z

Evaluation of depth image classification performance on the validation split of the SUN RGB-D dataset, reporting Top-1 Accuracy.

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 | Depth Image Classification |
| Dataset (including any stated split) | SUN RGB-D (SUN-D) (val) |
| Metric | Top-1 Accuracy |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/depth-image-classification-on-sun-rgb-d-val.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Supervised SOTA | 64.9 | Not recorded | 68fa72b21e209131cea57f66 |
| ViT-LENSL | 52.2 | Not recorded | 68fa72b21e209131cea57f66 |
| ViT-LENSL | 37.4 | Not recorded | 68fa72b21e209131cea57f66 |
| ImageBind-H | 35.1 | Not recorded | 68fa72b21e209131cea57f66 |
| Text Paired | 25.4 | Not recorded | 68fa72b21e209131cea57f66 |

### Supervised SOTA

Top-1 Accuracy: 64.9. Result ID: 69926e143a6c3148490ee631.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c2d1e209131cea328ef.md>)

[Implementation](<https://facebookresearch.github.io/omnivore>)

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

### ViT-LENSL

Top-1 Accuracy: 52.2. Result ID: 69926e143a6c3148490ee630.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Implementation](<https://github.com/TencentARC/ViT-Lens>)

Recorded evaluation configuration: {"anchor":"I+T"}. This record does not assert independent reproduction.

### ViT-LENSL

Top-1 Accuracy: 37.4. Result ID: 69926e143a6c3148490ee62f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Implementation](<https://github.com/TencentARC/ViT-Lens>)

Recorded evaluation configuration: {"anchor":"I"}. This record does not assert independent reproduction.

### ImageBind-H

Top-1 Accuracy: 35.1. Result ID: 69926e143a6c3148490ee62e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"anchor":"I"}. This record does not assert independent reproduction.

### Text Paired

Top-1 Accuracy: 25.4. Result ID: 69926e143a6c3148490ee62d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72b21e209131cea57f66.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f971e209131cea467c4.md>)

[Implementation](<https://facebookresearch.github.io/ImageBind>)

Recorded evaluation configuration: {"anchor":"T\*"}. This record does not assert independent reproduction.

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