# OOD Detection on BIMCV-COVID19+ (ID) vs CT-SCAN & X-Ray-Bone (OOD) OpenOOD setup (test)

Source: [OOD Detection on BIMCV-COVID19+ (ID) vs CT-SCAN & X-Ray-Bone (OOD) OpenOOD setup (test)](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test>)

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

Data updated: 2026-03-27T13:11:07.470Z

Evaluation of Out-of-Distribution (OOD) detection performance using the OpenOOD setup, where BIMCV-COVID19+ serves as the in-distribution data, tested against CT-SCAN and X-Ray-Bone as out-of-distribution sources, reporting segmented and averaged 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) | BIMCV-COVID19+ (ID) vs CT-SCAN & X-Ray-Bone (OOD) OpenOOD setup (test) |
| Metric | Average AUROC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Average AUROC](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=Average%20AUROC>): Higher is better; unit: PERCENT.

- [AUROC (CT-SCAN OOD)](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=AUROC%20(CT-SCAN%20OOD)>): Higher is better; unit: PERCENT.

- [FPR95 (CT-SCAN OOD)](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=FPR95%20(CT-SCAN%20OOD)>): Lower is better; unit: PERCENT.

- [AUROC (X-Ray-Bone OOD)](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=AUROC%20(X-Ray-Bone%20OOD)>): Higher is better; unit: PERCENT.

- [FPR95 (X-Ray-Bone OOD)](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=FPR95%20(X-Ray-Bone%20OOD)>): Lower is better; unit: PERCENT.

- [Average FPR95](<https://www.sota2.com/research/sota/ood-detection-on-bimcv-covid19-plus-id-vs-ct-scan-and-x-ray-bone-ood-openood-setup-test.md?metric=Average%20FPR95>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Average AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| TANL | 100 | Not recorded | 69c60f290636e5bf4afc85ba |
| AdaNeg | 99.99 | Not recorded | 69c60f290636e5bf4afc85ba |
| NegLabel | 99.68 | Not recorded | 69c60f290636e5bf4afc85ba |
| AdaNeg | 96.74 | Not recorded | 68fa75711e209131cea67f50 |
| NegLabel | 81.61 | Not recorded | 68fa75711e209131cea67f50 |

### TANL

Average AUROC: 100. Result ID: 69c681d847f34ce924b08ed6.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f290636e5bf4afc85ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60f290636e5bf4afc85ba.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AdaNeg

Average AUROC: 99.99. Result ID: 69c681d847f34ce924b08ed5.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f290636e5bf4afc85ba.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75711e209131cea67f50.md>)

[Implementation](<https://github.com/YBZh/OpenOOD-VLM>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NegLabel

Average AUROC: 99.68. Result ID: 69c681d847f34ce924b08ed4.

[Reporting paper](<https://www.sota2.com/research/paper/69c60f290636e5bf4afc85ba.md>)

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

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AdaNeg

Average AUROC: 96.74. Result ID: 6993a62b3a6c314849178ba6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75711e209131cea67f50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75711e209131cea67f50.md>)

[Implementation](<https://github.com/YBZh/OpenOOD-VLM>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16 CLIP","Memory Length (L)":"10"}. This record does not assert independent reproduction.

### NegLabel

Average AUROC: 81.61. Result ID: 6993a62b3a6c314849178ba5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa75711e209131cea67f50.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16 CLIP"}. This record does not assert independent reproduction.

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