# Image Classification on CIFAR-10 (short protocol (3 epochs))

Source: [Image Classification on CIFAR-10 (short protocol (3 epochs))](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-short-protocol-3-epochs>)

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

Data updated: 2026-07-07T09:54:22.926Z

Evaluation of Image Classification performance on the CIFAR-10 dataset using the specified short protocol, typically involving 3 epochs of training.

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) | CIFAR-10 (short protocol (3 epochs)) |
| Metric | Accuracy |
| Unit | SCALAR |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-short-protocol-3-epochs.md?metric=Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| vanilla Adam | 4 | Not recorded | 6a4c882985dba69fef8b2a13 |
| vanilla Adam | 0.537 | Not recorded | 6a4c882985dba69fef8b2a13 |
| Adam-InitOnly | 0.535 | Not recorded | 6a4c882985dba69fef8b2a13 |

### vanilla Adam

Accuracy: 4. Result ID: 6a4cccb860b88bb339ca0160.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882985dba69fef8b2a13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fca0b.md>)

Recorded evaluation configuration: {"Learning Rate":"10⁻³","Normalisation":"None","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

### vanilla Adam

Accuracy: 0.537. Result ID: 6a4cccb860b88bb339ca0161.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882985dba69fef8b2a13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63171e209131ce9fca0b.md>)

Recorded evaluation configuration: {"Learning Rate":"3×10⁻⁴","Normalisation":"None","Backbone":"ResNet-18","Tuning":"best tuned"}. This record does not assert independent reproduction.

### Adam-InitOnly

Accuracy: 0.535. Result ID: 6a4cccb860b88bb339ca0162.

[Reporting paper](<https://www.sota2.com/research/paper/6a4c882985dba69fef8b2a13.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a4c882985dba69fef8b2a13.md>)

Recorded evaluation configuration: {"Learning Rate":"10⁻³","Initialization Cap (kappa)":"0.05","Normalisation":"None","Backbone":"ResNet-18"}. This record does not assert independent reproduction.

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