# Image Classification on Caltech-101 all-to-all

Source: [Image Classification on Caltech-101 all-to-all](<https://www.sota2.com/research/sota/image-classification-on-caltech-101-all-to-all>)

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

Data updated: 2026-02-27T11:35:04.494Z

Evaluation of Image Classification performance on the Caltech-101 dataset using the all-to-all protocol, reporting 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) | Caltech-101 all-to-all |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-caltech-101-all-to-all.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Rep-Adapter + ADK | 94 | Not recorded | 6948d059423ea42265729d6c |
| Rep-Adapter | 93.9 | Not recorded | 6948d059423ea42265729d6c |
| 2SFS + ADK | 93.9 | Not recorded | 6948d059423ea42265729d6c |
| CLIP-LoRA + ADK | 93.6 | Not recorded | 6948d059423ea42265729d6c |
| 2SFS | 93.6 | Not recorded | 6948d059423ea42265729d6c |
| CLIP-LoRA | 93.2 | Not recorded | 6948d059423ea42265729d6c |
| CLIP | 92.9 | Not recorded | 6948d059423ea42265729d6c |

### Rep-Adapter + ADK

Accuracy: 94. Result ID: 69a1815935dfcabb00e77e52.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### Rep-Adapter

Accuracy: 93.9. Result ID: 69a1815935dfcabb00e77e51.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ed31e209131cea426f8.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### 2SFS + ADK

Accuracy: 93.9. Result ID: 69a1815935dfcabb00e77e56.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### CLIP-LoRA + ADK

Accuracy: 93.6. Result ID: 69a1815935dfcabb00e77e54.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### 2SFS

Accuracy: 93.6. Result ID: 69a1815935dfcabb00e77e55.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa777a1e209131cea736e6.md>)

[Implementation](<https://github.com/FarinaMatteo/rethinking_fewshot_vlms>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### CLIP-LoRA

Accuracy: 93.2. Result ID: 69a1815935dfcabb00e77e53.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73741e209131cea5c9ee.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

### CLIP

Accuracy: 92.9. Result ID: 69a1815935dfcabb00e77e50.

[Reporting paper](<https://www.sota2.com/research/paper/6948d059423ea42265729d6c.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training Dataset":"ImageNet","Evaluation Protocol":"all-to-all"}. This record does not assert independent reproduction.

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