# Image Classification on ImageNet occ

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

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

Data updated: 2026-02-26T05:33:00.546Z

Evaluation of Image Classification performance on the ImageNet occ dataset, focusing on Accuracy.

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 occ |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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-imagenet-occ.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PiT-S | 74.6 | Not recorded | 68fa6a8e1e209131cea28c41 |
| ViT-S | 73 | Not recorded | 68fa6a8e1e209131cea28c41 |
| CutMix | 71.51 | Not recorded | 68fa6d4e1e209131cea38f75 |
| HMix | 71.13 | Not recorded | 68fa6d4e1e209131cea38f75 |
| ResNet50 | 67.1 | Not recorded | 68fa6a8e1e209131cea28c41 |
| GMix | 62.76 | Not recorded | 68fa6d4e1e209131cea38f75 |
| Mixup | 60.34 | Not recorded | 68fa6d4e1e209131cea38f75 |
| Vanilla (no MDSA) | 55.26 | Not recorded | 68fa6d4e1e209131cea38f75 |
| ResNet50 | 52.2 | Not recorded | 68fa6a8e1e209131cea28c41 |

### PiT-S

Accuracy: 74.6. Result ID: 699aba275698665ec4481e6c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c41.md>)

[Implementation](<https://github.com/naver-ai/pit>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ViT-S

Accuracy: 73. Result ID: 699aba275698665ec4481e6d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69181e209131cea202b4.md>)

[Implementation](<https://github.com/facebookresearch/deit>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### CutMix

Accuracy: 71.51. Result ID: 698f9b663a6c314849fa78e1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa663d1e209131cea0f1ce.md>)

[Implementation](<https://github.com/clovaai/CutMix-PyTorch>)

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

### HMix

Accuracy: 71.13. Result ID: 698f9b663a6c314849fa78e2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Implementation](<https://github.com/naver-ai/hmix-gmix>)

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

### ResNet50

Accuracy: 67.1. Result ID: 699aba275698665ec4481e6f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"variant":"well-optimized (†)"}. This record does not assert independent reproduction.

### GMix

Accuracy: 62.76. Result ID: 698f9b663a6c314849fa78e3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Implementation](<https://github.com/naver-ai/hmix-gmix>)

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

### Mixup

Accuracy: 60.34. Result ID: 698f9b663a6c314849fa78e0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

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

### Vanilla (no MDSA)

Accuracy: 55.26. Result ID: 698f9b663a6c314849fa78df.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d4e1e209131cea38f75.md>)

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

### ResNet50

Accuracy: 52.2. Result ID: 699aba275698665ec4481e6e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a8e1e209131cea28c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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