# Image Classification Calibration on Tiny ImageNet C

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

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

Data updated: 2026-06-01T09:14:48.725Z

Evaluation of model calibration performance, including Expected Calibration Error (ECE) and Accuracy, on the corrupted Tiny ImageNet C dataset.

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 Calibration |
| Dataset (including any stated split) | Tiny ImageNet C |
| 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-calibration-on-tiny-imagenet-c.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Expected Calibration Error](<https://www.sota2.com/research/sota/image-classification-calibration-on-tiny-imagenet-c.md?metric=Expected%20Calibration%20Error>): Lower is better; unit: PERCENT.

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

- [Class-wise Expected Calibration Error](<https://www.sota2.com/research/sota/image-classification-calibration-on-tiny-imagenet-c.md?metric=Class-wise%20Expected%20Calibration%20Error>): Lower is better; unit: SCALAR.

- [Average Calibration Error](<https://www.sota2.com/research/sota/image-classification-calibration-on-tiny-imagenet-c.md?metric=Average%20Calibration%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Mixup | 26.26 | Not recorded | 68fa7af41e209131cea85f3e |
| LS-0.05 | 25.96 | Not recorded | 68fa7af41e209131cea85f3e |
| CE | 24.27 | Not recorded | 68fa7af41e209131cea85f3e |
| FGR | 24.03 | Not recorded | 68fa7af41e209131cea85f3e |
| DFL | 23.84 | Not recorded | 68fa7af41e209131cea85f3e |
| FLSD-53 | 22.3 | Not recorded | 68fa7af41e209131cea85f3e |
| BSCE-GRA | 21.47 | Not recorded | 68fa7af41e209131cea85f3e |
| MaxEnt M | 21.14 | Not recorded | 68fa7af41e209131cea85f3e |
| AugMix | 14.51 | Not recorded | 68fa7af41e209131cea85f3e |

### Mixup

Accuracy: 26.26. Result ID: 6a1d4d17fbc373592c16bd22.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69951e209131cea22d47.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### LS-0.05

Accuracy: 25.96. Result ID: 6a1d4d17fbc373592c16bd21.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67b71e209131cea180d7.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### CE

Accuracy: 24.27. Result ID: 6a1d4d17fbc373592c16bd20.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### FGR

Accuracy: 24.03. Result ID: 6a1d4d17fbc373592c16bd28.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### DFL

Accuracy: 23.84. Result ID: 6a1d4d17fbc373592c16bd25.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f681e209131cea45624.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### FLSD-53

Accuracy: 22.3. Result ID: 6a1d4d17fbc373592c16bd24.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a21e209131cea1d496.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### BSCE-GRA

Accuracy: 21.47. Result ID: 6a1d4d17fbc373592c16bd27.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77bd1e209131cea750a1.md>)

[Implementation](<https://github.com/Jinxu-Lin/BSCE-GRA>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### MaxEnt M

Accuracy: 21.14. Result ID: 6a1d4d17fbc373592c16bd26.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea565b2.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

### AugMix

Accuracy: 14.51. Result ID: 6a1d4d17fbc373592c16bd23.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f3e.md>)

Recorded evaluation configuration: {"Backbone":"DenseNet-121"}. This record does not assert independent reproduction.

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