# Out-of-distribution detection on Tiny ImageNet CROP (test)

Source: [Out-of-distribution detection on Tiny ImageNet CROP (test)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-tiny-imagenet-crop-test>)

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

Data updated: 2026-02-26T05:40:45.918Z

Evaluation of Out-of-Distribution detection performance using the test split of the cropped version of the Tiny ImageNet dataset.

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 | Out-of-distribution detection |
| Dataset (including any stated split) | Tiny ImageNet CROP (test) |
| Metric | Detection Accuracy |
| Unit | PERCENT |
| 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

- [Detection Accuracy](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-tiny-imagenet-crop-test.md?metric=Detection%20Accuracy>): Higher is better; unit: PERCENT.

- [AUROC](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-tiny-imagenet-crop-test.md?metric=AUROC>): Higher is better; unit: PERCENT.

- [AUPR (ID)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-tiny-imagenet-crop-test.md?metric=AUPR%20(ID)>): Higher is better; unit: PERCENT.

- [AUPR (OOD)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-tiny-imagenet-crop-test.md?metric=AUPR%20(OOD)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Detection Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AlignMixup/AE | 79.7 | Not recorded | 68fa6c1a1e209131cea322ed |
| AlignMixup | 77.2 | Not recorded | 68fa6c1a1e209131cea322ed |
| StyleCutMix | 75.3 | Not recorded | 68fa6c1a1e209131cea322ed |
| Saliency Mix | 73.3 | Not recorded | 68fa6c1a1e209131cea322ed |
| PuzzleMix | 71.8 | Not recorded | 68fa6c1a1e209131cea322ed |
| Co-Mixup | 71.5 | Not recorded | 68fa6c1a1e209131cea322ed |
| Cutmix | 70.4 | Not recorded | 68fa6c1a1e209131cea322ed |
| StyleMix | 67.8 | Not recorded | 68fa6c1a1e209131cea322ed |
| Manifold | 67.4 | Not recorded | 68fa6c1a1e209131cea322ed |
| Baseline | 61.2 | Not recorded | 68fa6c1a1e209131cea322ed |
| Input | 58.7 | Not recorded | 68fa6c1a1e209131cea322ed |

### AlignMixup/AE

Detection Accuracy: 79.7. Result ID: 698ed3ebffc3901de0a1ccba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Implementation](<https://github.com/shashankvkt/AlignMixup_CVPR22.git>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### AlignMixup

Detection Accuracy: 77.2. Result ID: 698ed3ebffc3901de0a1ccb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Implementation](<https://github.com/shashankvkt/AlignMixup_CVPR22.git>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### StyleCutMix

Detection Accuracy: 75.3. Result ID: 698ed3ebffc3901de0a1ccb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Saliency Mix

Detection Accuracy: 73.3. Result ID: 698ed3ebffc3901de0a1ccb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a771e209131cea28534.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### PuzzleMix

Detection Accuracy: 71.8. Result ID: 698ed3ebffc3901de0a1ccb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f91e209131cea1f6ad.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Co-Mixup

Detection Accuracy: 71.5. Result ID: 698ed3ebffc3901de0a1ccb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa693b1e209131cea21085.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Cutmix

Detection Accuracy: 70.4. Result ID: 698ed3ebffc3901de0a1ccb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa663d1e209131cea0f1ce.md>)

[Implementation](<https://github.com/clovaai/CutMix-PyTorch>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### StyleMix

Detection Accuracy: 67.8. Result ID: 698ed3ebffc3901de0a1ccb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Manifold

Detection Accuracy: 67.4. Result ID: 698ed3ebffc3901de0a1ccb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65bb1e209131cea0bec2.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Baseline

Detection Accuracy: 61.2. Result ID: 698ed3ebffc3901de0a1ccb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

### Input

Detection Accuracy: 58.7. Result ID: 698ed3ebffc3901de0a1ccb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6c1a1e209131cea322ed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e44.md>)

[Implementation](<https://github.com/facebookresearch/mixup-cifar10>)

Recorded evaluation configuration: {"Backbone":"PreActResnet18"}. This record does not assert independent reproduction.

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