# Robust Image Classification on ImageNet-1K (Zero-shot)

Source: [Robust Image Classification on ImageNet-1K (Zero-shot)](<https://www.sota2.com/research/sota/robust-image-classification-on-imagenet-1k-zero-shot>)

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

Data updated: 2026-02-27T13:16:44.080Z

Evaluation of Image Classification performance on ImageNet-1K focusing on robustness metrics, specifically reporting standard Robust Accuracy and Zero-shot Average Robust 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 | Classification |
| Dataset (including any stated split) | ImageNet-1K |
| Metric | Robust Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Robust Accuracy](<https://www.sota2.com/research/sota/robust-image-classification-on-imagenet-1k-zero-shot.md?metric=Robust%20Accuracy>): Higher is better; unit: PERCENT.

- [Zero-shot Avg Robust Acc](<https://www.sota2.com/research/sota/robust-image-classification-on-imagenet-1k-zero-shot.md?metric=Zero-shot%20Avg%20Robust%20Acc>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Robust Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SAFT-L | 24.53 | Not recorded | 6992a4ad9ebc499c97406d32 |
| SAFT-L | 20.22 | Not recorded | 6992a4ad9ebc499c97406d32 |
| TGA-ZSR | 19.89 | Not recorded | 6992a4ad9ebc499c97406d32 |
| TGA-ZSR | 19.2 | Not recorded | 6992a4ad9ebc499c97406d32 |
| PMG-AFT | 19.17 | Not recorded | 6992a4ad9ebc499c97406d32 |
| TeCoA | 16.21 | Not recorded | 6992a4ad9ebc499c97406d32 |
| TeCoA | 14.24 | Not recorded | 6992a4ad9ebc499c97406d32 |
| PMG-AFT | 12.92 | Not recorded | 6992a4ad9ebc499c97406d32 |

### SAFT-L

Robust Accuracy: 24.53. Result ID: 69a1992435dfcabb00e7dcb9.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

Recorded evaluation configuration: {"Attack Protocol":"C&W (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### SAFT-L

Robust Accuracy: 20.22. Result ID: 69a1992435dfcabb00e7dcb5.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

Recorded evaluation configuration: {"Attack Protocol":"AutoAttack (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### TGA-ZSR

Robust Accuracy: 19.89. Result ID: 69a1992435dfcabb00e7dcb8.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

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

Recorded evaluation configuration: {"Attack Protocol":"C&W (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### TGA-ZSR

Robust Accuracy: 19.2. Result ID: 69a1992435dfcabb00e7dcb4.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

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

Recorded evaluation configuration: {"Attack Protocol":"AutoAttack (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### PMG-AFT

Robust Accuracy: 19.17. Result ID: 69a1992435dfcabb00e7dcb3.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

Recorded evaluation configuration: {"Attack Protocol":"AutoAttack (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### TeCoA

Robust Accuracy: 16.21. Result ID: 69a1992435dfcabb00e7dcb2.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

Recorded evaluation configuration: {"Attack Protocol":"AutoAttack (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### TeCoA

Robust Accuracy: 14.24. Result ID: 69a1992435dfcabb00e7dcb6.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

Recorded evaluation configuration: {"Attack Protocol":"C&W (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

### PMG-AFT

Robust Accuracy: 12.92. Result ID: 69a1992435dfcabb00e7dcb7.

[Reporting paper](<https://www.sota2.com/research/paper/6992a4ad9ebc499c97406d32.md>)

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

Recorded evaluation configuration: {"Attack Protocol":"C&W (ϵ = 1/255)","Evaluation Setting":"zero-shot"}. This record does not assert independent reproduction.

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