Visual prompts built on robust source models inherit adversarial robustness but lose standard accuracy; a max-pooling over logit blocks (PBL) improves accuracy while keeping most robustness.
Adaptformer: Adapting vision transformers for scalable visual recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Visual Prompting: Robustness Inheritance and Beyond
Visual prompts built on robust source models inherit adversarial robustness but lose standard accuracy; a max-pooling over logit blocks (PBL) improves accuracy while keeping most robustness.