# OOD Detection on ImageNet far-OOD Places

Source: [OOD Detection on ImageNet far-OOD Places](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-far-ood-places>)

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

Data updated: 2026-04-28T09:08:27.156Z

Evaluation of Out-of-Distribution (OOD) detection performance using the ImageNet far-OOD dataset, specifically focusing on the 'Places' subset or configuration.

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 far-OOD Places |
| Metric | FPR95 |
| Unit | PERCENT |
| Direction | Lower is better |
| Results loaded | 9 of 9 |
| 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

- [FPR95](<https://www.sota2.com/research/sota/ood-detection-on-imagenet-far-ood-places.md?metric=FPR95>): Lower is better; unit: PERCENT.

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

## Recorded results

| Method | FPR95 | Result date | Report paper |
| --- | --- | --- | --- |
| DynProto | 26.63 | Not recorded | 69f03f5155a3c32af89fa34a |
| CADRef | 66.71 | Not recorded | 69f03f5155a3c32af89fa34a |
| MSP | 67.79 | Not recorded | 69f03f5155a3c32af89fa34a |
| OptFS | 68.63 | Not recorded | 69f03f5155a3c32af89fa34a |
| ReAct | 70.79 | Not recorded | 69f03f5155a3c32af89fa34a |
| VIM | 71.82 | Not recorded | 69f03f5155a3c32af89fa34a |
| Energy | 78.92 | Not recorded | 69f03f5155a3c32af89fa34a |
| DICE | 94.74 | Not recorded | 69f03f5155a3c32af89fa34a |
| ASH-S | 99.59 | Not recorded | 69f03f5155a3c32af89fa34a |

### DynProto

FPR95: 26.63. Result ID: 69f078fc47f34ce924d692f5.

[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":"Swin-B"}. This record does not assert independent reproduction.

### CADRef

FPR95: 66.71. Result ID: 69f078fc47f34ce924d692f4.

[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":"Swin-B"}. This record does not assert independent reproduction.

### MSP

FPR95: 67.79. Result ID: 69f078fc47f34ce924d692ed.

[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":"Swin-B"}. This record does not assert independent reproduction.

### OptFS

FPR95: 68.63. Result ID: 69f078fc47f34ce924d692f2.

[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":"Swin-B"}. This record does not assert independent reproduction.

### ReAct

FPR95: 70.79. Result ID: 69f078fc47f34ce924d692ef.

[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":"Swin-B"}. This record does not assert independent reproduction.

### VIM

FPR95: 71.82. Result ID: 69f078fc47f34ce924d692f3.

[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":"Swin-B"}. This record does not assert independent reproduction.

### Energy

FPR95: 78.92. Result ID: 69f078fc47f34ce924d692ee.

[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":"Swin-B"}. This record does not assert independent reproduction.

### DICE

FPR95: 94.74. Result ID: 69f078fc47f34ce924d692f0.

[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":"Swin-B"}. This record does not assert independent reproduction.

### ASH-S

FPR95: 99.59. Result ID: 69f078fc47f34ce924d692f1.

[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":"Swin-B"}. This record does not assert independent reproduction.

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