# Image Classification on Oxfordpets (Adversarial Robustness: Clean, PGD, CW, Auto Attack)

Source: [Image Classification on Oxfordpets (Adversarial Robustness: Clean, PGD, CW, Auto Attack)](<https://www.sota2.com/research/sota/image-classification-on-oxfordpets-adversarial-robustness-clean-pgd-cw-auto-attack>)

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

Data updated: 2026-02-27T11:46:09.436Z

Evaluation of Image Classification performance on the OxfordPets dataset, reporting clean accuracy and robustness against specific adversarial attacks (PGD, CW, AutoAttack).

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 | Image Classification |
| Dataset (including any stated split) | Oxfordpets |
| Metric | Clean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [Clean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxfordpets-adversarial-robustness-clean-pgd-cw-auto-attack.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [PGD Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxfordpets-adversarial-robustness-clean-pgd-cw-auto-attack.md?metric=PGD%20Accuracy>): Higher is better; unit: PERCENT.

- [CW Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxfordpets-adversarial-robustness-clean-pgd-cw-auto-attack.md?metric=CW%20Accuracy>): Higher is better; unit: PERCENT.

- [Auto Attack Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxfordpets-adversarial-robustness-clean-pgd-cw-auto-attack.md?metric=Auto%20Attack%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 87.41 | Not recorded | 6940e7a8456146936284f897 |
| FARE | 80.98 | Not recorded | 6940e7a8456146936284f897 |
| PMG-AFT | 79.4 | Not recorded | 6940e7a8456146936284f897 |
| UCAT | 74.16 | Not recorded | 6940e7a8456146936284f897 |
| TGA-ZSR | 68.44 | Not recorded | 6940e7a8456146936284f897 |
| TeCoA | 61.3 | Not recorded | 6940e7a8456146936284f897 |

### CLIP

Clean Accuracy: 87.41. Result ID: 69a183f135dfcabb00e7891b.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

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

### FARE

Clean Accuracy: 80.98. Result ID: 69a183f135dfcabb00e7891d.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738c1e209131cea5d24a.md>)

Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction.

### PMG-AFT

Clean Accuracy: 79.4. Result ID: 69a183f135dfcabb00e7891e.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72df1e209131cea5912e.md>)

Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction.

### UCAT

Clean Accuracy: 74.16. Result ID: 69a183f135dfcabb00e78920.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction.

### TGA-ZSR

Clean Accuracy: 68.44. Result ID: 69a183f135dfcabb00e7891f.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75771e209131cea68256.md>)

[Implementation](<https://github.com/zhyblue424/TGA-ZSR>)

Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction.

### TeCoA

Clean Accuracy: 61.3. Result ID: 69a183f135dfcabb00e7891c.

[Reporting paper](<https://www.sota2.com/research/paper/6940e7a8456146936284f897.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f271e209131cea44177.md>)

Recorded evaluation configuration: {"Fine-tuning dataset":"TinyImageNet","Adversarial training":"2-step PGD","Epsilon":"1/255"}. This record does not assert independent reproduction.

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