# Image Classification on STL-10 (Adversarial Robustness) Source: [Image Classification on STL-10 (Adversarial Robustness)]() Collection index: [llms.txt]() Data updated: 2026-03-31T08:14:05.706Z Evaluation of Image Classification performance on the STL-10 dataset, specifically measuring robustness via Top-1 Accuracy under clean and adversarial conditions. 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) | STL-10 | | Metric | Top-1 Accuracy (Clean) | | 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 - [Top-1 Accuracy (Clean)](): Higher is better; unit: PERCENT. - [Top-1 Accuracy (Adversarial)](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy (Clean) | Result date | Report paper | | --- | --- | --- | --- | | SPD | 97.38 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | WISE-FT | 97.26 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | TPGM | 97.25 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | GRACE | 97.1 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | Vanilla FT | 97.03 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | FLYP | 96 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | CLIP | 95.71 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | PMG-AFT | 88.9 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | FARE | 87.87 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | LAAT | 86.1 | Not recorded | 69cb54ee0636e5bf4afc9d9a | | TeCoA | 85.3 | Not recorded | 69cb54ee0636e5bf4afc9d9a | ### SPD Top-1 Accuracy (Clean): 97.38. Result ID: 69cb824347f34ce924b3b2ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### WISE-FT Top-1 Accuracy (Clean): 97.26. Result ID: 69cb824347f34ce924b3b2a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### TPGM Top-1 Accuracy (Clean): 97.25. Result ID: 69cb824347f34ce924b3b2aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### GRACE Top-1 Accuracy (Clean): 97.1. Result ID: 69cb824347f34ce924b3b2b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### Vanilla FT Top-1 Accuracy (Clean): 97.03. Result ID: 69cb824347f34ce924b3b2a7. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FLYP Top-1 Accuracy (Clean): 96. Result ID: 69cb824347f34ce924b3b2a9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### CLIP Top-1 Accuracy (Clean): 95.71. Result ID: 69cb824347f34ce924b3b2a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### PMG-AFT Top-1 Accuracy (Clean): 88.9. Result ID: 69cb824347f34ce924b3b2ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### FARE Top-1 Accuracy (Clean): 87.87. Result ID: 69cb824347f34ce924b3b2ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### LAAT Top-1 Accuracy (Clean): 86.1. Result ID: 69cb824347f34ce924b3b2af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. ### TeCoA Top-1 Accuracy (Clean): 85.3. Result ID: 69cb824347f34ce924b3b2ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"ViT-B/32","Pre-training Dataset":"ImageNet","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.