# Image Classification on D.Net-Cl 3-shot (test)

Source: [Image Classification on D.Net-Cl 3-shot (test)](<https://www.sota2.com/research/sota/image-classification-on-d-net-cl-3-shot-test>)

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

Data updated: 2026-02-26T05:30:22.901Z

Evaluation of Image Classification performance on the test split of the D.Net-Cl 3-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 3-shot (test) |
| 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-3-shot-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SA | 59.83 | Not recorded | 68fa77421e209131cea72108 |
| Linear Probing | 58.22 | Not recorded | 68fa77421e209131cea72108 |
| Fine Tuning | 55.74 | Not recorded | 68fa77421e209131cea72108 |
| Offsite Tuning | 55.03 | Not recorded | 68fa77421e209131cea72108 |
| Split Learning | 49.64 | Not recorded | 68fa77421e209131cea72108 |
| LN-TUNE | 7.32 | Not recorded | 68fa77421e209131cea72108 |

### SA

Accuracy: 59.83. Result ID: 69948e713a6c3148491dfb1b.

[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":"Swin-L"}. This record does not assert independent reproduction.

### Linear Probing

Accuracy: 58.22. Result ID: 69948e713a6c3148491dfb16.

[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":"Swin-L"}. This record does not assert independent reproduction.

### Fine Tuning

Accuracy: 55.74. Result ID: 69948e713a6c3148491dfb17.

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

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

### Offsite Tuning

Accuracy: 55.03. Result ID: 69948e713a6c3148491dfb1a.

[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":"Swin-L"}. This record does not assert independent reproduction.

### Split Learning

Accuracy: 49.64. Result ID: 69948e713a6c3148491dfb19.

[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":"Swin-L"}. This record does not assert independent reproduction.

### LN-TUNE

Accuracy: 7.32. Result ID: 69948e713a6c3148491dfb18.

[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":"Swin-L"}. This record does not assert independent reproduction.

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