# Image Classification on D.Net-Cl 10-shot

Source: [Image Classification on D.Net-Cl 10-shot](<https://www.sota2.com/research/sota/image-classification-on-d-net-cl-10-shot>)

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

Data updated: 2026-02-26T05:30:22.852Z

Evaluation of Image Classification performance on the D.Net-Cl 10-shot dataset, 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) | D.Net-Cl 10-shot |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-d-net-cl-10-shot.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SA | 58.27 | Not recorded | 68fa77421e209131cea72108 |
| Offsite Tuning | 52.58 | Not recorded | 68fa77421e209131cea72108 |
| Fine Tuning | 52.38 | Not recorded | 68fa77421e209131cea72108 |
| Linear Probing | 50.31 | Not recorded | 68fa77421e209131cea72108 |
| Split Learning | 48.33 | Not recorded | 68fa77421e209131cea72108 |
| LN-TUNE | 7.34 | Not recorded | 68fa77421e209131cea72108 |

### SA

Accuracy: 58.27. Result ID: 69948e713a6c3148491dfb09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Implementation](<https://github.com/conditionWang/Split_Adaptation>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

### Offsite Tuning

Accuracy: 52.58. Result ID: 69948e713a6c3148491dfb08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e7d1e209131cea4041d.md>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

### Fine Tuning

Accuracy: 52.38. Result ID: 69948e713a6c3148491dfb05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

### Linear Probing

Accuracy: 50.31. Result ID: 69948e713a6c3148491dfb04.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65de1e209131cea0cf4d.md>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

### Split Learning

Accuracy: 48.33. Result ID: 69948e713a6c3148491dfb07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa651b1e209131cea0859d.md>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

### LN-TUNE

Accuracy: 7.34. Result ID: 69948e713a6c3148491dfb06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77421e209131cea72108.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eee1e209131cea42f25.md>)

Recorded evaluation configuration: {"Backbone":"Deit-Base"}. This record does not assert independent reproduction.

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