# Few-shot classification on ImageNet and Variants domain generalization

Source: [Few-shot classification on ImageNet and Variants domain generalization](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization>)

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

Data updated: 2026-02-26T05:47:01.714Z

Evaluation of few-shot classification performance across the base ImageNet dataset and its out-of-distribution variants (V2, Sketch, A, R) to assess domain generalization capabilities.

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 | Few-shot classification |
| Dataset (including any stated split) | ImageNet and Variants domain generalization |
| Metric | ImageNet Source Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [ImageNet Source Acc](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization.md?metric=ImageNet%20Source%20Acc>): Higher is better; unit: PERCENT.

- [ImageNet-V2 Acc](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization.md?metric=ImageNet-V2%20Acc>): Higher is better; unit: PERCENT.

- [ImageNet-Sketch Acc](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization.md?metric=ImageNet-Sketch%20Acc>): Higher is better; unit: PERCENT.

- [ImageNet-A Acc](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization.md?metric=ImageNet-A%20Acc>): Higher is better; unit: PERCENT.

- [ImageNet-R Acc](<https://www.sota2.com/research/sota/few-shot-classification-on-imagenet-and-variants-domain-generalization.md?metric=ImageNet-R%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | ImageNet Source Acc | Result date | Report paper |
| --- | --- | --- | --- |
| AAPE | 73.56 | Not recorded | 68fa75731e209131cea68013 |
| ArGue-N | 71.84 | Not recorded | 68fa75731e209131cea68013 |
| ProText | 70.22 | Not recorded | 68fa75731e209131cea68013 |

### AAPE

ImageNet Source Acc: 73.56. Result ID: 6993c0063a6c314849184403.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75731e209131cea68013.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75731e209131cea68013.md>)

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

### ArGue-N

ImageNet Source Acc: 71.84. Result ID: 6993c0063a6c314849184402.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75731e209131cea68013.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72821e209131cea56e20.md>)

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

### ProText

ImageNet Source Acc: 70.22. Result ID: 6993c0063a6c314849184401.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75731e209131cea68013.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71bc1e209131cea52d9b.md>)

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

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