# Image Classification on DTD (Robustness and Accuracy Metrics)

Source: [Image Classification on DTD (Robustness and Accuracy Metrics)](<https://www.sota2.com/research/sota/image-classification-on-dtd-robustness-and-accuracy-metrics>)

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

Data updated: 2026-04-07T09:42:42.908Z

Evaluation of Image Classification performance on the Describable Textures Dataset (DTD), reporting robustness and general accuracy scores.

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 | Robustness Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

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

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

## Recorded results

| Method | Robustness Score | Result date | Report paper |
| --- | --- | --- | --- |
| ATAC | 76.06 | Not recorded | 6923e676d6b0dd334292eee0 |
| R-TPT | 26.97 | Not recorded | 6923e676d6b0dd334292eee0 |
| TTC | 11.4 | Not recorded | 6923e676d6b0dd334292eee0 |
| TTE | 7.16 | Not recorded | 6923e676d6b0dd334292eee0 |
| PMG-AFT | 5.21 | Not recorded | 6923e676d6b0dd334292eee0 |
| TeCoA | 5.16 | Not recorded | 6923e676d6b0dd334292eee0 |
| FARE | 2.5 | Not recorded | 6923e676d6b0dd334292eee0 |
| CLIP | 0.11 | Not recorded | 6923e676d6b0dd334292eee0 |
| CLIP-FT | 0 | Not recorded | 6923e676d6b0dd334292eee0 |

### ATAC

Robustness Score: 76.06. Result ID: 69d4d19047f34ce924bcfd65.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

Recorded evaluation configuration: {"Defense Category":"Test-time Defense"}. This record does not assert independent reproduction.

### R-TPT

Robustness Score: 26.97. Result ID: 69d4d19047f34ce924bcfd64.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7add1e209131cea8590d.md>)

[Implementation](<https://github.com/TomSheng21/R-TPT>)

Recorded evaluation configuration: {"Defense Category":"Test-time Defense"}. This record does not assert independent reproduction.

### TTC

Robustness Score: 11.4. Result ID: 69d4d19047f34ce924bcfd63.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa774a1e209131cea724cc.md>)

[Implementation](<https://www.sota2.com/here>)

Recorded evaluation configuration: {"Defense Category":"Test-time Defense"}. This record does not assert independent reproduction.

### TTE

Robustness Score: 7.16. Result ID: 69d4d19047f34ce924bcfd62.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a711e209131cea2817e.md>)

Recorded evaluation configuration: {"Defense Category":"Test-time Defense"}. This record does not assert independent reproduction.

### PMG-AFT

Robustness Score: 5.21. Result ID: 69d4d19047f34ce924bcfd60.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

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

Recorded evaluation configuration: {"Defense Category":"Adversarial Finetuning"}. This record does not assert independent reproduction.

### TeCoA

Robustness Score: 5.16. Result ID: 69d4d19047f34ce924bcfd5f.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

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

Recorded evaluation configuration: {"Defense Category":"Adversarial Finetuning"}. This record does not assert independent reproduction.

### FARE

Robustness Score: 2.5. Result ID: 69d4d19047f34ce924bcfd61.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

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

Recorded evaluation configuration: {"Defense Category":"Adversarial Finetuning"}. This record does not assert independent reproduction.

### CLIP

Robustness Score: 0.11. Result ID: 69d4d19047f34ce924bcfd5d.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

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

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

Recorded evaluation configuration: {"Defense Category":"None"}. This record does not assert independent reproduction.

### CLIP-FT

Robustness Score: 0. Result ID: 69d4d19047f34ce924bcfd5e.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

Recorded evaluation configuration: {"Defense Category":"Adversarial Finetuning"}. This record does not assert independent reproduction.

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