# Out-of-Distribution Detection on CIFAR-10 (ID) vs LSUN-C (OOD)

Source: [Out-of-Distribution Detection on CIFAR-10 (ID) vs LSUN-C (OOD)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-cifar-10-id-vs-lsun-c-ood>)

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

Data updated: 2026-04-28T09:08:26.933Z

Evaluation of Out-of-Distribution Detection performance using CIFAR-10 as the in-distribution dataset and LSUN-C as the out-of-distribution dataset, reporting FPR95 and AUROC.

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 | Out-of-Distribution Detection |
| Dataset (including any stated split) | CIFAR-10 (ID) vs LSUN-C (OOD) |
| Metric | FPR@95 |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 16 of 16 |
| 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

- [FPR@95](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-cifar-10-id-vs-lsun-c-ood.md?metric=FPR%4095>): Lower is better; unit: PERCENT.

- [AUROC](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-cifar-10-id-vs-lsun-c-ood.md?metric=AUROC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FPR@95 | Result date | Report paper |
| --- | --- | --- | --- |
| DynProto | 0.11 | Not recorded | 69f03f5155a3c32af89fa34a |
| AdaND | 0.35 | Not recorded | 69f03f5155a3c32af89fa34a |
| MCM | 5.77 | Not recorded | 69f03f5155a3c32af89fa34a |
| DynProto | 6.04 | Not recorded | 69f03f5155a3c32af89fa34a |
| CADRef | 7.02 | Not recorded | 69f03f5155a3c32af89fa34a |
| GLMCM | 7.49 | Not recorded | 69f03f5155a3c32af89fa34a |
| DICE | 8.85 | Not recorded | 69f03f5155a3c32af89fa34a |
| ASH-S | 9.67 | Not recorded | 69f03f5155a3c32af89fa34a |
| VIM | 15.42 | Not recorded | 69f03f5155a3c32af89fa34a |
| NegLabel | 15.48 | Not recorded | 69f03f5155a3c32af89fa34a |
| NegRefine | 15.52 | Not recorded | 69f03f5155a3c32af89fa34a |
| Energy | 15.62 | Not recorded | 69f03f5155a3c32af89fa34a |
| OptFS | 18.32 | Not recorded | 69f03f5155a3c32af89fa34a |
| CSP | 19.99 | Not recorded | 69f03f5155a3c32af89fa34a |
| MSP | 47.09 | Not recorded | 69f03f5155a3c32af89fa34a |
| ReAct | 87.22 | Not recorded | 69f03f5155a3c32af89fa34a |

### DynProto

FPR@95: 0.11. Result ID: 69f078fc47f34ce924d69210.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### AdaND

FPR@95: 0.35. Result ID: 69f078fc47f34ce924d6920f.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77e11e209131cea75c33.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### MCM

FPR@95: 5.77. Result ID: 69f078fc47f34ce924d6920a.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e0a1e209131cea3d9c6.md>)

[Implementation](<https://github.com/deeplearning-wisc/MCM>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### DynProto

FPR@95: 6.04. Result ID: 69f078fc47f34ce924d69209.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### CADRef

FPR@95: 7.02. Result ID: 69f078fc47f34ce924d69208.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77761e209131cea734a1.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### GLMCM

FPR@95: 7.49. Result ID: 69f078fc47f34ce924d6920b.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### DICE

FPR@95: 8.85. Result ID: 69f078fc47f34ce924d69204.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfc1e209131cea371c4.md>)

[Implementation](<https://github.com/deeplearning-wisc/dice.git>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### ASH-S

FPR@95: 9.67. Result ID: 69f078fc47f34ce924d69205.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f371e209131cea447f1.md>)

[Implementation](<https://andrijazz.github.io/ash>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### VIM

FPR@95: 15.42. Result ID: 69f078fc47f34ce924d69207.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c151e209131cea32091.md>)

[Implementation](<https://github.com/haoqiwang/vim>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### NegLabel

FPR@95: 15.48. Result ID: 69f078fc47f34ce924d6920c.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72b01e209131cea57e55.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### NegRefine

FPR@95: 15.52. Result ID: 69f078fc47f34ce924d6920d.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a1c1e209131cea813fd.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### Energy

FPR@95: 15.62. Result ID: 69f078fc47f34ce924d69202.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69cc1e209131cea24242.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### OptFS

FPR@95: 18.32. Result ID: 69f078fc47f34ce924d69206.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72121e209131cea544f5.md>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### CSP

FPR@95: 19.99. Result ID: 69f078fc47f34ce924d6920e.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75351e209131cea666f2.md>)

Recorded evaluation configuration: {"Backbone":"CLIP-B/16","Method Category":"Vision Language Model based Methods"}. This record does not assert independent reproduction.

### MSP

FPR@95: 47.09. Result ID: 69f078fc47f34ce924d69201.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64e41e209131cea0731a.md>)

[Implementation](<https://www.sota2.com/github.com/hendrycks/error-detection>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

### ReAct

FPR@95: 87.22. Result ID: 69f078fc47f34ce924d69203.

[Reporting paper](<https://www.sota2.com/research/paper/69f03f5155a3c32af89fa34a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b4f1e209131cea2d8b5.md>)

[Implementation](<https://github.com/deeplearning-wisc/react.git>)

Recorded evaluation configuration: {"Backbone":"ResNet50","Method Category":"Vision Model based Methods"}. This record does not assert independent reproduction.

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