# Few-shot image classification on Omniglot Meta-Training Alphabets (train)

Source: [Few-shot image classification on Omniglot Meta-Training Alphabets (train)](<https://www.sota2.com/research/sota/few-shot-image-classification-on-omniglot-meta-training-alphabets-train>)

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

Data updated: 2026-02-26T05:35:32.509Z

Evaluation of few-shot image classification performance specifically on the meta-training split of the Omniglot dataset, reporting risk-sensitive metrics like Average, Worst, and CVaRα.

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 image classification |
| Dataset (including any stated split) | Omniglot Meta-Training Alphabets (train) |
| Metric | Average Performance |
| 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

- [Average Performance](<https://www.sota2.com/research/sota/few-shot-image-classification-on-omniglot-meta-training-alphabets-train.md?metric=Average%20Performance>): Higher is better; unit: PERCENT.

- [Worst Performance](<https://www.sota2.com/research/sota/few-shot-image-classification-on-omniglot-meta-training-alphabets-train.md?metric=Worst%20Performance>): Higher is better; unit: PERCENT.

- [CVaRα](<https://www.sota2.com/research/sota/few-shot-image-classification-on-omniglot-meta-training-alphabets-train.md?metric=CVaR%CE%B1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Performance | Result date | Report paper |
| --- | --- | --- | --- |
| DR-MAML | 99.6 | Not recorded | 68fa70b61e209131cea4cbd4 |
| MAML | 99.2 | Not recorded | 68fa70b61e209131cea4cbd4 |
| MAML | 98.4 | Not recorded | 68fa70b61e209131cea4cbd4 |
| TR-MAML | 97.4 | Not recorded | 68fa70b61e209131cea4cbd4 |
| DR-MAML | 97.1 | Not recorded | 68fa70b61e209131cea4cbd4 |
| TR-MAML | 92.2 | Not recorded | 68fa70b61e209131cea4cbd4 |

### DR-MAML

Average Performance: 99.6. Result ID: 699155353a6c3148490760d3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Implementation](<https://github.com/lgcollins/tr-maml>)

Recorded evaluation configuration: {"N-way":"20-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

### MAML

Average Performance: 99.2. Result ID: 699155353a6c3148490760d1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

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

Recorded evaluation configuration: {"N-way":"20-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

### MAML

Average Performance: 98.4. Result ID: 699155353a6c3148490760ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

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

Recorded evaluation configuration: {"N-way":"5-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

### TR-MAML

Average Performance: 97.4. Result ID: 699155353a6c3148490760cf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa57051e209131ce9a1c56.md>)

Recorded evaluation configuration: {"N-way":"5-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

### DR-MAML

Average Performance: 97.1. Result ID: 699155353a6c3148490760d0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Implementation](<https://github.com/lgcollins/tr-maml>)

Recorded evaluation configuration: {"N-way":"5-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

### TR-MAML

Average Performance: 92.2. Result ID: 699155353a6c3148490760d2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70b61e209131cea4cbd4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa57051e209131ce9a1c56.md>)

Recorded evaluation configuration: {"N-way":"20-way","K-shot":"1-shot"}. This record does not assert independent reproduction.

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