# Classification on ImageNet Adversarial (IN-A) (test)

Source: [Classification on ImageNet Adversarial (IN-A) (test)](<https://www.sota2.com/research/sota/classification-on-imagenet-adversarial-in-a-test>)

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

Data updated: 2026-02-27T07:54:01.793Z

Evaluation of Classification performance (Top-1 Accuracy) on the test split of the ImageNet Adversarial (IN-A) dataset.

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 Adversarial (IN-A) (test) |
| Metric | Top-1 Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Top-1 Accuracy](<https://www.sota2.com/research/sota/classification-on-imagenet-adversarial-in-a-test.md?metric=Top-1%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| RILS | 12.1 | Not recorded | 68fa6eaf1e209131cea416fe |
| MAE+CLIP | 11.6 | Not recorded | 68fa6eaf1e209131cea416fe |
| SLIP | 10.5 | Not recorded | 68fa6eaf1e209131cea416fe |
| CLIP | 9.3 | Not recorded | 68fa6eaf1e209131cea416fe |

### RILS

Top-1 Accuracy: 12.1. Result ID: 69a14d8b35dfcabb00e62167.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416fe.md>)

[Implementation](<https://github.com/hustvl/RILS>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Zero-shot":"true","Training Epochs":"25","Training Data":"L-20M"}. This record does not assert independent reproduction.

### MAE+CLIP

Top-1 Accuracy: 11.6. Result ID: 69a14d8b35dfcabb00e62166.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416fe.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Zero-shot":"true","Training Epochs":"25","Training Data":"L-20M"}. This record does not assert independent reproduction.

### SLIP

Top-1 Accuracy: 10.5. Result ID: 69a14d8b35dfcabb00e62165.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416fe.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7a1e209131cea2e67a.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/16","Zero-shot":"true","Training Epochs":"25","Training Data":"L-20M"}. This record does not assert independent reproduction.

### CLIP

Top-1 Accuracy: 9.3. Result ID: 69a14d8b35dfcabb00e62164.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6eaf1e209131cea416fe.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","Zero-shot":"true","Training Epochs":"25","Training Data":"L-20M"}. This record does not assert independent reproduction.

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