# Few-shot Image Classification on ImageNet (Novel/All Split)

Source: [Few-shot Image Classification on ImageNet (Novel/All Split)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-novel-all-split>)

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

Data updated: 2026-02-26T05:53:58.053Z

Evaluation of few-shot image classification performance on a specific configuration of ImageNet, measured using Novel Top-5 Accuracy and All Top-5 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) | ImageNet few-shot |
| Metric | Novel Top-5 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 0 of 0 |
| 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

- [Novel Top-5 Acc](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-novel-all-split.md?metric=Novel%20Top-5%20Acc>): Higher is better; unit: PERCENT.

- [All Top-5 Acc](<https://www.sota2.com/research/sota/few-shot-image-classification-on-imagenet-novel-all-split.md?metric=All%20Top-5%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Novel Top-5 Acc | Result date | Report paper |
| --- | --- | --- | --- |

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