# Anomaly Detection on VAND Challenge zero-shot track 2023

Source: [Anomaly Detection on VAND Challenge zero-shot track 2023](<https://www.sota2.com/research/sota/anomaly-detection-on-vand-challenge-zero-shot-track-2023>)

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

Data updated: 2026-02-26T05:43:53.748Z

Evaluation of Anomaly Detection performance on the VAND Challenge 2023 dataset, specifically using the zero-shot track setup.

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 | Anomaly Detection |
| Dataset (including any stated split) | VAND Challenge zero-shot track 2023 |
| Metric | F1 Score (Max) |
| 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

- [F1 Score (Max)](<https://www.sota2.com/research/sota/anomaly-detection-on-vand-challenge-zero-shot-track-2023.md?metric=F1%20Score%20(Max)>): Higher is better; unit: PERCENT.

- [F1 Score (Segmentation Max)](<https://www.sota2.com/research/sota/anomaly-detection-on-vand-challenge-zero-shot-track-2023.md?metric=F1%20Score%20(Segmentation%20Max)>): Higher is better; unit: PERCENT.

- [F1 Score (Classification Max)](<https://www.sota2.com/research/sota/anomaly-detection-on-vand-challenge-zero-shot-track-2023.md?metric=F1%20Score%20(Classification%20Max)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score (Max) | Result date | Report paper |
| --- | --- | --- | --- |
| APRIL-GAN | 45.89 | Not recorded | 68fa70d71e209131cea4d95d |
| SegmentAnyAnomaly | 39.56 | Not recorded | 68fa70d71e209131cea4d95d |
| Variance Vigilance Vanguard | 32.17 | Not recorded | 68fa70d71e209131cea4d95d |
| MediaBrain | 28.8 | Not recorded | 68fa70d71e209131cea4d95d |
| AaxJIjQ | 27.88 | Not recorded | 68fa70d71e209131cea4d95d |

### APRIL-GAN

F1 Score (Max): 45.89. Result ID: 69915c773a6c314849079c07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

[Implementation](<https://github.com/ByChelsea/VAND-APRIL-GAN>)

Recorded evaluation configuration: {"track":"zero-shot"}. This record does not assert independent reproduction.

### SegmentAnyAnomaly

F1 Score (Max): 39.56. Result ID: 69915c773a6c314849079c08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

Recorded evaluation configuration: {"track":"zero-shot"}. This record does not assert independent reproduction.

### Variance Vigilance Vanguard

F1 Score (Max): 32.17. Result ID: 69915c773a6c314849079c09.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

Recorded evaluation configuration: {"track":"zero-shot"}. This record does not assert independent reproduction.

### MediaBrain

F1 Score (Max): 28.8. Result ID: 69915c773a6c314849079c0a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

Recorded evaluation configuration: {"track":"zero-shot"}. This record does not assert independent reproduction.

### AaxJIjQ

F1 Score (Max): 27.88. Result ID: 69915c773a6c314849079c0b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d95d.md>)

Recorded evaluation configuration: {"track":"zero-shot"}. This record does not assert independent reproduction.

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