# Anomaly Classification on VAND Challenge Few-shot track 2023

Source: [Anomaly Classification on VAND Challenge Few-shot track 2023](<https://www.sota2.com/research/sota/anomaly-classification-on-vand-challenge-few-shot-track-2023>)

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

Data updated: 2026-02-26T05:43:57.517Z

Evaluation of Anomaly Classification performance on the VAND Challenge Few-shot track 2023 dataset, reporting metrics such as F1-max-cls, F1-max, and Rank.

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 Classification |
| Dataset (including any stated split) | VAND Challenge Few-shot track 2023 |
| Metric | F1-max (cls) |
| 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-max (cls)](<https://www.sota2.com/research/sota/anomaly-classification-on-vand-challenge-few-shot-track-2023.md?metric=F1-max%20(cls)>): Higher is better; unit: PERCENT.

- [F1-max](<https://www.sota2.com/research/sota/anomaly-classification-on-vand-challenge-few-shot-track-2023.md?metric=F1-max>): Higher is better; unit: PERCENT.

- [Rank](<https://www.sota2.com/research/sota/anomaly-classification-on-vand-challenge-few-shot-track-2023.md?metric=Rank>): Lower is better; unit: SCALAR.

## Recorded results

| Method | F1-max (cls) | Result date | Report paper |
| --- | --- | --- | --- |
| APRIL-GAN | 86.87 | Not recorded | 68fa70d71e209131cea4d95d |
| MediaBrain | 84.8 | Not recorded | 68fa70d71e209131cea4d95d |
| PatchCore+ | 84.23 | Not recorded | 68fa70d71e209131cea4d95d |
| Scortex | 83.99 | Not recorded | 68fa70d71e209131cea4d95d |
| WinCLIP | 81.14 | Not recorded | 68fa70d71e209131cea4d95d |

### APRIL-GAN

F1-max (cls): 86.87. Result ID: 69915c773a6c314849079c01.

[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":"Few-shot"}. This record does not assert independent reproduction.

### MediaBrain

F1-max (cls): 84.8. Result ID: 69915c773a6c314849079bff.

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

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

### PatchCore+

F1-max (cls): 84.23. Result ID: 69915c773a6c314849079bfe.

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

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

### Scortex

F1-max (cls): 83.99. Result ID: 69915c773a6c314849079c00.

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

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

### WinCLIP

F1-max (cls): 81.14. Result ID: 69915c773a6c314849079bfd.

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

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eea1e209131cea42e2d.md>)

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

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