# Many-shot Classification on mini-ImageNet (test)

Source: [Many-shot Classification on mini-ImageNet (test)](<https://www.sota2.com/research/sota/many-shot-classification-on-mini-imagenet-test>)

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

Data updated: 2026-02-26T05:21:19.312Z

Evaluation of Many-shot Classification performance on the test split of the mini-ImageNet dataset, reporting accuracy for specific N-way K-shot configurations (e.g., 5-way 100-shot, 10-way 50-shot).

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 | Many-shot Classification |
| Dataset (including any stated split) | mini-ImageNet (test) |
| Metric | 5-way 100-shot Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [5-way 100-shot Acc](<https://www.sota2.com/research/sota/many-shot-classification-on-mini-imagenet-test.md?metric=5-way%20100-shot%20Acc>): Higher is better; unit: PERCENT.

- [10-way 50-shot Acc](<https://www.sota2.com/research/sota/many-shot-classification-on-mini-imagenet-test.md?metric=10-way%2050-shot%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | 5-way 100-shot Acc | Result date | Report paper |
| --- | --- | --- | --- |
| GradNCP | 73.45 | Not recorded | 68fa70f71e209131cea4e6ff |
| MAML | 66.03 | Not recorded | 68fa70f71e209131cea4e6ff |

### GradNCP

5-way 100-shot Acc: 73.45. Result ID: 699169083a6c31484907f4f5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f71e209131cea4e6ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70f71e209131cea4e6ff.md>)

[Implementation](<https://github.com/jihoontack/GradNCP>)

Recorded evaluation configuration: {"Backbone":"Conv4","Number of trials":"3","Protocol":"In-domain adaptation"}. This record does not assert independent reproduction.

### MAML

5-way 100-shot Acc: 66.03. Result ID: 699169083a6c31484907f4f4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70f71e209131cea4e6ff.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63861e209131ce9ff3e8.md>)

Recorded evaluation configuration: {"Backbone":"Conv4","Number of trials":"3","Protocol":"In-domain adaptation"}. This record does not assert independent reproduction.

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