# Novelty Detection on CIFAR-10 vs CIFAR-100

Source: [Novelty Detection on CIFAR-10 vs CIFAR-100](<https://www.sota2.com/research/sota/novelty-detection-on-cifar-10-vs-cifar-100>)

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

Data updated: 2026-02-26T05:25:51.558Z

Evaluation of Novelty Detection performance comparing CIFAR-10 and CIFAR-100 datasets, measured by metrics such as AUROC.

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 | Novelty Detection |
| Dataset (including any stated split) | CIFAR-10vs100 |
| Metric | AUROC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [AUROC](<https://www.sota2.com/research/sota/novelty-detection-on-cifar-10-vs-cifar-100.md?metric=AUROC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUROC | Result date | Report paper |
| --- | --- | --- | --- |
| FITYMI | 0.9 | Not recorded | 68fa6e061e209131cea3d7db |
| Transformaly | 0.823 | Not recorded | 68fa6e061e209131cea3d7db |
| MSAD | 0.795 | Not recorded | 68fa6e061e209131cea3d7db |
| PANDA | 0.768 | Not recorded | 68fa6e061e209131cea3d7db |
| CSI | 0.761 | Not recorded | 68fa6e061e209131cea3d7db |
| MHRot | 0.631 | Not recorded | 68fa6e061e209131cea3d7db |
| GT | 0.626 | Not recorded | 68fa6e061e209131cea3d7db |
| ADIB | 0.607 | Not recorded | 68fa6e061e209131cea3d7db |
| DN2 | 0.585 | Not recorded | 68fa6e061e209131cea3d7db |
| DeepSAD | 0.5 | Not recorded | 68fa6e061e209131cea3d7db |
| One-class-OpenGAN | 0.5 | Not recorded | 68fa6e061e209131cea3d7db |

### FITYMI

AUROC: 0.9. Result ID: 699000163a6c314849fd5f45.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Implementation](<https://github.com/rohban-lab/FITYMI>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### Transformaly

AUROC: 0.823. Result ID: 699000163a6c314849fd5f44.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cfc1e209131cea371d2.md>)

[Implementation](<https://github.com/MatanCohen1/Transformaly>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### MSAD

AUROC: 0.795. Result ID: 699000163a6c314849fd5f43.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68c21e209131cea1e1d5.md>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### PANDA

AUROC: 0.768. Result ID: 699000163a6c314849fd5f42.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a911e209131cea28ebd.md>)

[Implementation](<https://github.com/talreiss/PANDA>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### CSI

AUROC: 0.761. Result ID: 699000163a6c314849fd5f3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68881e209131cea1cb66.md>)

[Implementation](<https://github.com/alinlab/CSI>)

Recorded evaluation configuration: {"Training":"From Scratch"}. This record does not assert independent reproduction.

### MHRot

AUROC: 0.631. Result ID: 699000163a6c314849fd5f3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66911e209131cea10f30.md>)

[Implementation](<https://github.com/hendrycks/ss-ood>)

Recorded evaluation configuration: {"Training":"From Scratch","Require Extra Outlier Exposure Datasets":true}. This record does not assert independent reproduction.

### GT

AUROC: 0.626. Result ID: 699000163a6c314849fd5f3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65161e209131cea082d3.md>)

[Implementation](<https://github.com/izikgo/AnomalyDetectionTransformations>)

Recorded evaluation configuration: {"Training":"From Scratch","Require Extra Outlier Exposure Datasets":true}. This record does not assert independent reproduction.

### ADIB

AUROC: 0.607. Result ID: 699000163a6c314849fd5f40.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### DN2

AUROC: 0.585. Result ID: 699000163a6c314849fd5f41.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67181e209131cea141be.md>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

### DeepSAD

AUROC: 0.5. Result ID: 699000163a6c314849fd5f3b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67091e209131cea14040.md>)

Recorded evaluation configuration: {"Training":"From Scratch","Require Extra Outlier Exposure Datasets":true}. This record does not assert independent reproduction.

### One-class-OpenGAN

AUROC: 0.5. Result ID: 699000163a6c314849fd5f3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e061e209131cea3d7db.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6af71e209131cea2b6a6.md>)

Recorded evaluation configuration: {"Training":"Pre-trained"}. This record does not assert independent reproduction.

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