# Image Classification on Office-Home Open (test)

Source: [Image Classification on Office-Home Open (test)](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test>)

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

Data updated: 2026-02-26T05:34:08.916Z

Evaluation of Image Classification performance on the test split of the Office-Home Open dataset variant, reporting accuracy across the four constituent domains (Art, Clipart, Product, Real) and the overall mean 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 | Image Classification |
| Dataset (including any stated split) | Office-Home Open (test) |
| Metric | Accuracy (Art) |
| 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

- [Accuracy (Art)](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test.md?metric=Accuracy%20(Art)>): Higher is better; unit: PERCENT.

- [Accuracy (Clipart)](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test.md?metric=Accuracy%20(Clipart)>): Higher is better; unit: PERCENT.

- [Accuracy (Product)](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test.md?metric=Accuracy%20(Product)>): Higher is better; unit: PERCENT.

- [Accuracy (Real)](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test.md?metric=Accuracy%20(Real)>): Higher is better; unit: PERCENT.

- [Mean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-office-home-open-test.md?metric=Mean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Art) | Result date | Report paper |
| --- | --- | --- | --- |
| Any-shift Prompting | 83.4 | Not recorded | 68fa72351e209131cea54ecc |
| CoCoOp | 80.93 | Not recorded | 68fa72351e209131cea54ecc |
| CoOp | 80.5 | Not recorded | 68fa72351e209131cea54ecc |
| CLIP-D | 80.47 | Not recorded | 68fa72351e209131cea54ecc |
| CLIP | 79.32 | Not recorded | 68fa72351e209131cea54ecc |

### Any-shift Prompting

Accuracy (Art): 83.4. Result ID: 6992247b3a6c3148490ce157.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

Recorded evaluation configuration: {"author-provided code":true}. This record does not assert independent reproduction.

### CoCoOp

Accuracy (Art): 80.93. Result ID: 6992247b3a6c3148490ce156.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea1167d.md>)

[Implementation](<https://github.com/HaohanWang/PAR>)

Recorded evaluation configuration: {"author-provided code":true}. This record does not assert independent reproduction.

### CoOp

Accuracy (Art): 80.5. Result ID: 6992247b3a6c3148490ce155.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d2b.md>)

Recorded evaluation configuration: {"author-provided code":true}. This record does not assert independent reproduction.

### CLIP-D

Accuracy (Art): 80.47. Result ID: 6992247b3a6c3148490ce154.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"author-provided code":true}. This record does not assert independent reproduction.

### CLIP

Accuracy (Art): 79.32. Result ID: 6992247b3a6c3148490ce153.

[Reporting paper](<https://www.sota2.com/research/paper/68fa72351e209131cea54ecc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"author-provided code":true,"zero-shot":true}. This record does not assert independent reproduction.

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