# Image Classification on Oxford Flowers (zero-shot)

Source: [Image Classification on Oxford Flowers (zero-shot)](<https://www.sota2.com/research/sota/image-classification-on-oxford-flowers-zero-shot>)

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

Data updated: 2026-03-31T08:14:05.797Z

Evaluation of Image Classification performance on the zero-shot setting of the Oxford Flowers dataset, reporting Clean Accuracy and Adversarial Accuracy.

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) | Oxford Flowers zero-shot |
| Metric | Clean 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

- [Clean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxford-flowers-zero-shot.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [Adversarial Accuracy](<https://www.sota2.com/research/sota/image-classification-on-oxford-flowers-zero-shot.md?metric=Adversarial%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRACE | 75.8 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| Vanilla FT | 75.6 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| TPGM | 74.2 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| SPD | 73.8 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| FLYP | 73.4 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| WISE-FT | 71.8 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| CLIP | 67.42 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| FARE | 58.4 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| PMG-AFT | 42.96 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| LAAT | 40.1 | Not recorded | 69cb54ee0636e5bf4afc9d9a |
| TeCoA | 36.13 | Not recorded | 69cb54ee0636e5bf4afc9d9a |

### GRACE

Clean Accuracy: 75.8. Result ID: 69cb824347f34ce924b3b2fd.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### Vanilla FT

Clean Accuracy: 75.6. Result ID: 69cb824347f34ce924b3b2f4.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### TPGM

Clean Accuracy: 74.2. Result ID: 69cb824347f34ce924b3b2f7.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6edf1e209131cea428cb.md>)

[Implementation](<https://github.com/PotatoTian/TPGM>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### SPD

Clean Accuracy: 73.8. Result ID: 69cb824347f34ce924b3b2f8.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75841e209131cea6855b.md>)

[Implementation](<https://github.com/GT-RIPL/Selective-Projection-Decay.git>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### FLYP

Clean Accuracy: 73.4. Result ID: 69cb824347f34ce924b3b2f6.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e241e209131cea3e1b0.md>)

[Implementation](<https://github.com/locuslab/FLYP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### WISE-FT

Clean Accuracy: 71.8. Result ID: 69cb824347f34ce924b3b2f5.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cd31e209131cea3601a.md>)

[Implementation](<https://github.com/mlfoundations/wise-ft>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### CLIP

Clean Accuracy: 67.42. Result ID: 69cb824347f34ce924b3b2f3.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

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

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### FARE

Clean Accuracy: 58.4. Result ID: 69cb824347f34ce924b3b2fa.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### PMG-AFT

Clean Accuracy: 42.96. Result ID: 69cb824347f34ce924b3b2fb.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### LAAT

Clean Accuracy: 40.1. Result ID: 69cb824347f34ce924b3b2fc.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72701e209131cea5651c.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

### TeCoA

Clean Accuracy: 36.13. Result ID: 69cb824347f34ce924b3b2f9.

[Reporting paper](<https://www.sota2.com/research/paper/69cb54ee0636e5bf4afc9d9a.md>)

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

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Training":"ImageNet","Evaluation":"Zero-shot"}. This record does not assert independent reproduction.

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