# Image Classification on CIFAR-100 (ECE and Calibration Metrics)

Source: [Image Classification on CIFAR-100 (ECE and Calibration Metrics)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics>)

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

Data updated: 2026-05-21T12:35:25.459Z

Evaluation of standard Image Classification performance on the CIFAR-100 dataset, focusing specifically on model calibration and uncertainty quantification metrics, including Expected Calibration Error (ECE) and Negative Log Likelihood (NLL).

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-100 |
| Metric | LCE |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 10 of 10 |
| 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

- [LCE](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=LCE>): Lower is better; unit: SCALAR.

- [MLCE](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=MLCE>): Lower is better; unit: SCALAR.

- [ECCE](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=ECCE>): Lower is better; unit: SCALAR.

- [ECE](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=ECE>): Lower is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [NLL](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-ece-and-calibration-metrics.md?metric=NLL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | LCE | Result date | Report paper |
| --- | --- | --- | --- |
| VQ | 0.0017 | Not recorded | 6a0e91b4f984739ed6738c73 |
| LN | 0.0024 | Not recorded | 6a0e91b4f984739ed6738c73 |
| DC | 0.0027 | Not recorded | 6a0e91b4f984739ed6738c73 |
| SM | 0.0031 | Not recorded | 6a0e91b4f984739ed6738c73 |
| IR | 0.0031 | Not recorded | 6a0e91b4f984739ed6738c73 |
| NC | 0.0032 | Not recorded | 6a0e91b4f984739ed6738c73 |
| TS | 0.0034 | Not recorded | 6a0e91b4f984739ed6738c73 |
| PC | 0.0041 | Not recorded | 6a0e91b4f984739ed6738c73 |
| KC | 0.0043 | Not recorded | 6a0e91b4f984739ed6738c73 |
| PS | 0.0053 | Not recorded | 6a0e91b4f984739ed6738c73 |

### VQ

LCE: 0.0017. Result ID: 6a0efaaefbc373592c0786a1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

### LN

LCE: 0.0024. Result ID: 6a0efaaefbc373592c0786a5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690442653ef7ccd74e5e496a.md>)

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

### DC

LCE: 0.0027. Result ID: 6a0efaaefbc373592c0786a3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

### SM

LCE: 0.0031. Result ID: 6a0efaaefbc373592c0786a2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/690c2baa2828b7cc6937c70f.md>)

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

### IR

LCE: 0.0031. Result ID: 6a0efaaefbc373592c0786a7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

### NC

LCE: 0.0032. Result ID: 6a0efaaefbc373592c0786aa.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

### TS

LCE: 0.0034. Result ID: 6a0efaaefbc373592c0786a8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

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

### PC

LCE: 0.0041. Result ID: 6a0efaaefbc373592c0786a9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72941e209131cea573f5.md>)

[Implementation](<https://github.com/MiaoXiong2320/ProximityBias-Calibration.git>)

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

### KC

LCE: 0.0043. Result ID: 6a0efaaefbc373592c0786a4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2e1e209131cea3e62b.md>)

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

### PS

LCE: 0.0053. Result ID: 6a0efaaefbc373592c0786a6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91b4f984739ed6738c73.md>)

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

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