# Image Classification on DTD (Adversarial Robustness)

Source: [Image Classification on DTD (Adversarial Robustness)](<https://www.sota2.com/research/sota/image-classification-on-dtd-adversarial-robustness>)

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

Data updated: 2026-02-27T11:46:09.457Z

Evaluation of Image Classification performance on the Describable Textures Dataset (DTD), reporting robustness metrics against various adversarial attacks (e.g., PGD, CW).

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) | DTD |
| 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-dtd-adversarial-robustness.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

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

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

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

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CLIP | 40.64 | Not recorded | 6940e7a8456146936284f897 |
| PMG-AFT | 32.45 | Not recorded | 6940e7a8456146936284f897 |
| UCAT | 31.92 | Not recorded | 6940e7a8456146936284f897 |
| TGA-ZSR | 25.69 | Not recorded | 6940e7a8456146936284f897 |
| TeCoA | 24.95 | Not recorded | 6940e7a8456146936284f897 |
| FARE | 23.09 | Not recorded | 6940e7a8456146936284f897 |

### CLIP

Clean Accuracy: 40.64. Result ID: 69a183f135dfcabb00e78927.

[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.

### PMG-AFT

Clean Accuracy: 32.45. Result ID: 69a183f135dfcabb00e7892a.

[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: 31.92. Result ID: 69a183f135dfcabb00e7892c.

[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: 25.69. Result ID: 69a183f135dfcabb00e7892b.

[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: 24.95. Result ID: 69a183f135dfcabb00e78928.

[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.

### FARE

Clean Accuracy: 23.09. Result ID: 69a183f135dfcabb00e78929.

[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.

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