# Image Classification on CIFAR10 (test) (Representation Accuracy %)

Source: [Image Classification on CIFAR10 (test) (Representation Accuracy %)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent>)

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

Data updated: 2026-02-26T05:59:44.804Z

Evaluation of Image Classification performance on the CIFAR-10 test set, reporting Representation Accuracy (RA %) derived from various self-supervised learning methods (e.g., SimCLR, MoCo).

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) | CIFAR10 (test) |
| Metric | RA (W-MSE) |
| 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

- [RA (W-MSE)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(W-MSE)>): Higher is better; unit: PERCENT.

- [RA (SimCLR)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(SimCLR)>): Higher is better; unit: PERCENT.

- [RA (NNCLR)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(NNCLR)>): Higher is better; unit: PERCENT.

- [RA (MoCo2+)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(MoCo2%2B)>): Higher is better; unit: PERCENT.

- [RA (MoCo3)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(MoCo3)>): Higher is better; unit: PERCENT.

- [RA (AVG)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-test-representation-accuracy-percent.md?metric=RA%20(AVG)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | RA (W-MSE) | Result date | Report paper |
| --- | --- | --- | --- |
| ZePAD | 79.99 | Not recorded | 698eb024c97a0b3e3b5e6766 |
| Baseline | 10.09 | Not recorded | 698eb024c97a0b3e3b5e6766 |

### ZePAD

RA (W-MSE): 79.99. Result ID: 6998cdbd5698665ec4314789.

[Reporting paper](<https://www.sota2.com/research/paper/698eb024c97a0b3e3b5e6766.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698eb024c97a0b3e3b5e6766.md>)

Recorded evaluation configuration: {"MAPE-Branch":"CLIP","Adversarial fine-tuning":"CIFAR10","Batch size":64,"Learning rate":0.00001,"Hyperparameter λ":20}. This record does not assert independent reproduction.

### Baseline

RA (W-MSE): 10.09. Result ID: 6998cdbd5698665ec4314788.

[Reporting paper](<https://www.sota2.com/research/paper/698eb024c97a0b3e3b5e6766.md>)

Recorded evaluation configuration: {"MAPE-Branch":"CLIP","Adversarial fine-tuning":"CIFAR10","Batch size":64,"Learning rate":0.00001,"Hyperparameter λ":20}. This record does not assert independent reproduction.

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