# Image Classification on ImageNet (val) (Accuracy (Clean))

Source: [Image Classification on ImageNet (val) (Accuracy (Clean))](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-clean>)

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

Data updated: 2026-02-26T05:34:12.211Z

Evaluation of Image Classification performance on the validation split of the ImageNet dataset, reporting the specific metric 'Accuracy (Clean)'.

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) | ImageNet (val) |
| Metric | Accuracy (Clean) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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 (Clean)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-clean.md?metric=Accuracy%20(Clean)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Clean) | Result date | Report paper |
| --- | --- | --- | --- |
| AugMix | 77.5 | Not recorded | 68fa6d351e209131cea386e2 |
| PRIME | 77 | Not recorded | 68fa6d351e209131cea386e2 |
| DA | 76.7 | Not recorded | 68fa6d351e209131cea386e2 |
| Standard | 76.1 | Not recorded | 68fa6d351e209131cea386e2 |

### AugMix

Accuracy (Clean): 77.5. Result ID: 698f83ed3a6c314849f99140.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9aa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### PRIME

Accuracy (Clean): 77. Result ID: 698f83ed3a6c314849f99142.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386e2.md>)

[Implementation](<https://github.com/amodas/PRIME-augmentations>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### DA

Accuracy (Clean): 76.7. Result ID: 698f83ed3a6c314849f99141.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9aa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### Standard

Accuracy (Clean): 76.1. Result ID: 698f83ed3a6c314849f9913f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d351e209131cea386e2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b2d1e209131cea2c9aa.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-50"}. This record does not assert independent reproduction.

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