# Image Classification on ImageNet-C Severity 1

Source: [Image Classification on ImageNet-C Severity 1](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1>)

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

Data updated: 2026-04-07T07:11:17.217Z

Evaluation of Image Classification performance on the ImageNet-C dataset corrupted specifically at Severity Level 1.

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-C Severity 1 |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Top-1 Acc](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

- [Smoothed ECE](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Smoothed%20ECE>): Lower is better; unit: PERCENT.

- [Top-1 Acc (Gaussian Blur)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Gaussian%20Blur)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Shot Noise)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Shot%20Noise)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Impulse Noise)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Impulse%20Noise)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Defocus Blur)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Defocus%20Blur)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Glass Blur)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Glass%20Blur)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Motion Blur)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Motion%20Blur)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Zoom Blur)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Zoom%20Blur)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Snow)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Snow)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Frost)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Frost)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Fog)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Fog)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Brightness)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Brightness)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Contrast)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Contrast)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Elastic)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Elastic)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Pixelate)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Pixelate)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (JPEG Compression)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(JPEG%20Compression)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (Average)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-c-severity-1.md?metric=Top-1%20Acc%20(Average)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| Reference Masking Regularization | 75.24 | Not recorded | 68fa73731e209131cea5c97b |
| Reference Masking Regularization | 74.7 | Not recorded | 68fa73731e209131cea5c97b |
| Standard | 74.48 | Not recorded | 68fa73731e209131cea5c97b |
| Standard | 74.45 | Not recorded | 68fa73731e209131cea5c97b |
| Reference Masking Regularization | 72.52 | Not recorded | 68fa73731e209131cea5c97b |
| Standard | 72.37 | Not recorded | 68fa73731e209131cea5c97b |
| Reference Masking Regularization | 72.13 | Not recorded | 68fa73731e209131cea5c97b |
| Standard | 71.63 | Not recorded | 68fa73731e209131cea5c97b |

### Reference Masking Regularization

Top-1 Acc: 75.24. Result ID: 6992ed033a6c31484912678a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-B","Parameters":"87.8M"}. This record does not assert independent reproduction.

### Reference Masking Regularization

Top-1 Acc: 74.7. Result ID: 6992ed033a6c314849126786.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-S","Parameters":"49.7M"}. This record does not assert independent reproduction.

### Standard

Top-1 Acc: 74.48. Result ID: 6992ed033a6c314849126785.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-S","Parameters":"49.7M"}. This record does not assert independent reproduction.

### Standard

Top-1 Acc: 74.45. Result ID: 6992ed033a6c314849126789.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-B","Parameters":"87.8M"}. This record does not assert independent reproduction.

### Reference Masking Regularization

Top-1 Acc: 72.52. Result ID: 6992ed033a6c314849126788.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"VITb16","Parameters":"86.3M"}. This record does not assert independent reproduction.

### Standard

Top-1 Acc: 72.37. Result ID: 6992ed033a6c314849126787.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"VITb16","Parameters":"86.3M"}. This record does not assert independent reproduction.

### Reference Masking Regularization

Top-1 Acc: 72.13. Result ID: 6992ed033a6c314849126784.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-T","Parameters":"28.4M"}. This record does not assert independent reproduction.

### Standard

Top-1 Acc: 71.63. Result ID: 6992ed033a6c314849126783.

[Reporting paper](<https://www.sota2.com/research/paper/68fa73731e209131cea5c97b.md>)

Recorded evaluation configuration: {"Backbone":"SWINv2-T","Parameters":"28.4M"}. This record does not assert independent reproduction.

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