# Image Classification on CIFAR-10 (Clean, C, and PGD Accuracy)

Source: [Image Classification on CIFAR-10 (Clean, C, and PGD Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-clean-c-and-pgd-accuracy>)

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

Data updated: 2026-03-27T12:48:30.298Z

Evaluation of Image Classification performance on CIFAR-10, reporting standard clean accuracy alongside robustness metrics measured against specific corruption (C) and Projected Gradient Descent (PGD) attacks.

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 |
| Metric | Clean Top-1 Accuracy |
| 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

- [Clean Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-clean-c-and-pgd-accuracy.md?metric=Clean%20Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [C Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-clean-c-and-pgd-accuracy.md?metric=C%20Top-1%20Accuracy>): Higher is better; unit: PERCENT.

- [PGD Top-1 Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-clean-c-and-pgd-accuracy.md?metric=PGD%20Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FractalDB | 96 | Not recorded | 69c60efa0636e5bf4afc8498 |
| Fractal arts | 95.8 | Not recorded | 69c60efa0636e5bf4afc8498 |
| Baseline | 95.6 | Not recorded | 69c60efa0636e5bf4afc8498 |
| VisualAtom | 95.6 | Not recorded | 69c60efa0636e5bf4afc8498 |
| MoireDB (Ours, Static) | 95.4 | Not recorded | 69c60efa0636e5bf4afc8498 |
| FVis | 95.2 | Not recorded | 69c60efa0636e5bf4afc8498 |

### FractalDB

Clean Top-1 Accuracy: 96. Result ID: 69c67c0c47f34ce924b06282.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69151e209131cea201a3.md>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4","Data Augmentation Pipeline":"PixMix"}. This record does not assert independent reproduction.

### Fractal arts

Clean Top-1 Accuracy: 95.8. Result ID: 69c67c0c47f34ce924b06280.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4","Data Augmentation Pipeline":"PixMix"}. This record does not assert independent reproduction.

### Baseline

Clean Top-1 Accuracy: 95.6. Result ID: 69c67c0c47f34ce924b0627f.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4"}. This record does not assert independent reproduction.

### VisualAtom

Clean Top-1 Accuracy: 95.6. Result ID: 69c67c0c47f34ce924b06283.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaa1e209131cea41395.md>)

[Implementation](<https://masora1030.github.io/Visual-Atoms-Pre-training-Vision-Transformers-with-Sinusoidal-Waves/>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4","Data Augmentation Pipeline":"PixMix"}. This record does not assert independent reproduction.

### MoireDB (Ours, Static)

Clean Top-1 Accuracy: 95.4. Result ID: 69c67c0c47f34ce924b06284.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4","Data Augmentation Pipeline":"PixMix"}. This record does not assert independent reproduction.

### FVis

Clean Top-1 Accuracy: 95.2. Result ID: 69c67c0c47f34ce924b06281.

[Reporting paper](<https://www.sota2.com/research/paper/69c60efa0636e5bf4afc8498.md>)

Recorded evaluation configuration: {"Backbone":"WideResNet-40-4","Data Augmentation Pipeline":"PixMix"}. This record does not assert independent reproduction.

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