# Classification Calibration on CIFAR-10 LT-100 (test)

Source: [Classification Calibration on CIFAR-10 LT-100 (test)](<https://www.sota2.com/research/sota/classification-calibration-on-cifar-10-lt-100-test>)

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

Data updated: 2026-02-26T05:21:39.087Z

Evaluation of model classification calibration performance on the test split of the CIFAR-10 LT-100 dataset, measured using metrics like ACE, TACE, SCE, 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 | Classification Calibration |
| Dataset (including any stated split) | CIFAR-10 LT-100 (test) |
| Metric | ACE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [ACE](<https://www.sota2.com/research/sota/classification-calibration-on-cifar-10-lt-100-test.md?metric=ACE>): Lower is better; unit: SCALAR.

- [TACE](<https://www.sota2.com/research/sota/classification-calibration-on-cifar-10-lt-100-test.md?metric=TACE>): Lower is better; unit: SCALAR.

- [SCE](<https://www.sota2.com/research/sota/classification-calibration-on-cifar-10-lt-100-test.md?metric=SCE>): Lower is better; unit: SCALAR.

- [BS](<https://www.sota2.com/research/sota/classification-calibration-on-cifar-10-lt-100-test.md?metric=BS>): Lower is better; unit: SCALAR.

## Recorded results

| Method | ACE | Result date | Report paper |
| --- | --- | --- | --- |
| UniMix+Bayias | 2.31 | Not recorded | 68fa6b331e209131cea2cd8f |
| Bayias | 2.45 | Not recorded | 68fa6b331e209131cea2cd8f |
| UniMix | 3.48 | Not recorded | 68fa6b331e209131cea2cd8f |
| Remix | 3.49 | Not recorded | 68fa6b331e209131cea2cd8f |
| LDAM+DRW | 4.14 | Not recorded | 68fa6b331e209131cea2cd8f |
| mixup | 4.87 | Not recorded | 68fa6b331e209131cea2cd8f |
| ERM | 5.42 | Not recorded | 68fa6b331e209131cea2cd8f |

### UniMix+Bayias

ACE: 2.31. Result ID: 698e70d5ffc3901de09d9d2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### Bayias

ACE: 2.45. Result ID: 698e70d5ffc3901de09d9d2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### UniMix

ACE: 3.48. Result ID: 698e70d5ffc3901de09d9d2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### Remix

ACE: 3.49. Result ID: 698e70d5ffc3901de09d9d2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c41e209131cea1e3de.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### LDAM+DRW

ACE: 4.14. Result ID: 698e70d5ffc3901de09d9d2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66901e209131cea10e0f.md>)

[Implementation](<https://github.com/kaidic/LDAM-DRW>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### mixup

ACE: 4.87. Result ID: 698e70d5ffc3901de09d9d2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

### ERM

ACE: 5.42. Result ID: 698e70d5ffc3901de09d9d29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b331e209131cea2cd8f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-32"}. This record does not assert independent reproduction.

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