# OOD Detection on ImageNet-1K OOD Benchmarks Overall Average

Source: [OOD Detection on ImageNet-1K OOD Benchmarks Overall Average](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-1k-ood-benchmarks-overall-average>)

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

Data updated: 2026-04-30T07:24:26.317Z

Evaluation of Out-of-Distribution (OOD) detection performance using ImageNet-1K as the in-distribution baseline, reporting the overall average performance across an unspecified set of OOD benchmarks. Key metrics are AUROC and FPR95.

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 | OOD Detection |
| Dataset (including any stated split) | ImageNet-1K OOD Benchmarks Overall Average |
| 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/ood-detection-on-imagenet-1k-ood-benchmarks-overall-average.md?metric=FPR%4095>): Lower is better; unit: PERCENT.

- [AUROC](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-1k-ood-benchmarks-overall-average.md?metric=AUROC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FPR@95 | Result date | Report paper |
| --- | --- | --- | --- |
| EPD | 40.96 | Not recorded | 69f2e22e55a3c32af89fc781 |
| RMDS | 43.4 | Not recorded | 69f2e22e55a3c32af89fc781 |
| MDS | 44.43 | Not recorded | 69f2e22e55a3c32af89fc781 |
| SHE | 44.63 | Not recorded | 69f2e22e55a3c32af89fc781 |
| ViM | 47.02 | Not recorded | 69f2e22e55a3c32af89fc781 |
| KNN | 47.35 | Not recorded | 69f2e22e55a3c32af89fc781 |
| GEN | 47.65 | Not recorded | 69f2e22e55a3c32af89fc781 |
| MSP | 63.75 | Not recorded | 69f2e22e55a3c32af89fc781 |
| DICE | 65.23 | Not recorded | 69f2e22e55a3c32af89fc781 |
| TempScale | 66.11 | Not recorded | 69f2e22e55a3c32af89fc781 |
| ReAct | 66.15 | Not recorded | 69f2e22e55a3c32af89fc781 |
| OpenMax | 68.81 | Not recorded | 69f2e22e55a3c32af89fc781 |
| MLS | 84.44 | Not recorded | 69f2e22e55a3c32af89fc781 |
| EBO | 88.49 | Not recorded | 69f2e22e55a3c32af89fc781 |
| GradNorm | 93.47 | Not recorded | 69f2e22e55a3c32af89fc781 |
| ASH | 95.84 | Not recorded | 69f2e22e55a3c32af89fc781 |

### EPD

FPR@95: 40.96. Result ID: 69f303a547f34ce924d91159.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### RMDS

FPR@95: 43.4. Result ID: 69f303a547f34ce924d91155.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### MDS

FPR@95: 44.43. Result ID: 69f303a547f34ce924d91150.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64f91e209131cea077ac.md>)

[Implementation](<https://github.com/pokaxpoka/deep_Mahalanobis_detector>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### SHE

FPR@95: 44.63. Result ID: 69f303a547f34ce924d91156.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### ViM

FPR@95: 47.02. Result ID: 69f303a547f34ce924d91158.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### KNN

FPR@95: 47.35. Result ID: 69f303a547f34ce924d9114f.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2f1e209131cea3e69b.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### GEN

FPR@95: 47.65. Result ID: 69f303a547f34ce924d9114d.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### MSP

FPR@95: 63.75. Result ID: 69f303a547f34ce924d91152.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.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":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### DICE

FPR@95: 65.23. Result ID: 69f303a547f34ce924d9114b.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### TempScale

FPR@95: 66.11. Result ID: 69f303a547f34ce924d91157.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### ReAct

FPR@95: 66.15. Result ID: 69f303a547f34ce924d91154.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### OpenMax

FPR@95: 68.81. Result ID: 69f303a547f34ce924d91153.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### MLS

FPR@95: 84.44. Result ID: 69f303a547f34ce924d91151.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### EBO

FPR@95: 88.49. Result ID: 69f303a547f34ce924d9114c.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### GradNorm

FPR@95: 93.47. Result ID: 69f303a547f34ce924d9114e.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6afd1e209131cea2b8e2.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

### ASH

FPR@95: 95.84. Result ID: 69f303a547f34ce924d9114a.

[Reporting paper](<https://www.sota2.com/research/paper/69f2e22e55a3c32af89fc781.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","ID Accuracy":"81.14%","ID Dataset":"ImageNet-1K"}. This record does not assert independent reproduction.

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