# Calibration on ImageNet-C

Source: [Calibration on ImageNet-C](<https://www.sota2.com/research/sota/calibration-on-imagenet-c>)

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

Data updated: 2026-02-26T05:59:49.161Z

Evaluation of model calibration performance on the ImageNet-C benchmark suite, typically measured using metrics like Root Mean Square Error (RMS).

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 | Calibration |
| Dataset (including any stated split) | ImageNet-C |
| Metric | RMS |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [RMS](<https://www.sota2.com/research/sota/calibration-on-imagenet-c.md?metric=RMS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | RMS | Result date | Report paper |
| --- | --- | --- | --- |
| PIXMIX | 6.3 | Not recorded | 68fa6c1d1e209131cea32540 |
| SIN | 6.5 | Not recorded | 68fa6c1d1e209131cea32540 |
| Mixup | 7.3 | Not recorded | 68fa6c1d1e209131cea32540 |
| AutoAugment | 8 | Not recorded | 68fa6c1d1e209131cea32540 |
| CutMix | 9.1 | Not recorded | 68fa6c1d1e209131cea32540 |
| AugMix | 9.2 | Not recorded | 68fa6c1d1e209131cea32540 |
| Cutout | 11.1 | Not recorded | 68fa6c1d1e209131cea32540 |
| Baseline | 12 | Not recorded | 68fa6c1d1e209131cea32540 |

### PIXMIX

RMS: 6.3. Result ID: 698edf24ffc3901de0a27b16.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Implementation](<https://github.com/andyzoujm/pixmix>)

Recorded evaluation configuration: {"Backbone":"ResNet-50","k":4,"beta":4}. This record does not assert independent reproduction.

### SIN

RMS: 6.5. Result ID: 698edf24ffc3901de0a27b15.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5f3a1e209131ce9e8680.md>)

[Implementation](<https://github.com/rgeirhos/texture-vs-shape>)

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

### Mixup

RMS: 7.3. Result ID: 698edf24ffc3901de0a27b11.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.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.

### AutoAugment

RMS: 8. Result ID: 698edf24ffc3901de0a27b13.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a51e209131cea0b94a.md>)

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

### CutMix

RMS: 9.1. Result ID: 698edf24ffc3901de0a27b12.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.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.

### AugMix

RMS: 9.2. Result ID: 698edf24ffc3901de0a27b14.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b421e209131cea2d07e.md>)

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

### Cutout

RMS: 11.1. Result ID: 698edf24ffc3901de0a27b10.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63d61e209131cea01202.md>)

[Implementation](<https://github.com/uoguelph-mlrg/Cutout>)

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

### Baseline

RMS: 12. Result ID: 698edf24ffc3901de0a27b0f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1d1e209131cea32540.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.