# Image Classification on CIFAR-10 (Uncertainty & Calibration)

Source: [Image Classification on CIFAR-10 (Uncertainty & Calibration)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration>)

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

Data updated: 2026-06-16T09:40:47.091Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, focusing on model calibration and uncertainty quantification metrics such as ECE, NLL, and Brier Score.

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) | CIFAR-10 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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-cifar-10-uncertainty-and-calibration.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AURC](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=AURC>): Higher is better; unit: SCALAR.

- [Calibration (1/2) %](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=Calibration%20(1%2F2)%20%25>): Higher is better; unit: PERCENT.

- [Calibration (1) %](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=Calibration%20(1)%20%25>): Higher is better; unit: PERCENT.

- [NLL](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=NLL>): Lower is better; unit: SCALAR.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=ECE>): Lower is better; unit: SCALAR.

- [Brier Score](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-uncertainty-and-calibration.md?metric=Brier%20Score>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CVP | 80.3 | Not recorded | 6a30d902d33dfb23e783d166 |
| Mean Network | 79.9 | Not recorded | 6a30d902d33dfb23e783d166 |
| Mean Network + Temp. Sc. | 79.9 | Not recorded | 6a30d902d33dfb23e783d166 |
| Streamlining | 79.8 | Not recorded | 6a30d902d33dfb23e783d166 |
| MC Sampling (4 samples) | 79.3 | Not recorded | 6a30d902d33dfb23e783d166 |
| MC Sampling (2 samples) | 78.3 | Not recorded | 6a30d902d33dfb23e783d166 |

### CVP

Accuracy: 80.3. Result ID: 6a311a0bfbc373592c2dda70.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

Recorded evaluation configuration: {"Rel. Time":"2.2×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

### Mean Network

Accuracy: 79.9. Result ID: 6a311a0bfbc373592c2dda6b.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

Recorded evaluation configuration: {"Rel. Time":"0.9×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

### Mean Network + Temp. Sc.

Accuracy: 79.9. Result ID: 6a311a0bfbc373592c2dda6c.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa638b1e209131ce9ff6d1.md>)

Recorded evaluation configuration: {"Rel. Time":"0.9×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

### Streamlining

Accuracy: 79.8. Result ID: 6a311a0bfbc373592c2dda6f.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a2c1e209131cea818ad.md>)

Recorded evaluation configuration: {"Rel. Time":"2.0×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

### MC Sampling (4 samples)

Accuracy: 79.3. Result ID: 6a311a0bfbc373592c2dda6e.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

Recorded evaluation configuration: {"Rel. Time":"4.0×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

### MC Sampling (2 samples)

Accuracy: 78.3. Result ID: 6a311a0bfbc373592c2dda6d.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d902d33dfb23e783d166.md>)

Recorded evaluation configuration: {"Rel. Time":"2.0×","Backbone":"sub-tiny ViT"}. This record does not assert independent reproduction.

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