
A novel forward-only adaptation method that learns prompts via a derivative-free optimizer and aligns activations to the source domain, enabling efficient test-time adaptation on resource-constrained devices without backpropagation.


coremsg

test-time-adaptation-of-vision-transformers-with-forward-only-prompt-learning


Test-Time Adaptation of Vision Transformers with Forward-Only Prompt Learning


title_rewrite


Optimal Transport-guided visual prompting (OT-VP) effectively aligns the target domain representation with the source domain representation, enabling Vision Transformer models to adapt to unseen domains without modifying the pre-trained model parameters.


optimal-transport-guided-visual-prompting-for-enhancing-vision-transformer-performance-on-unseen-domains


Optimal Transport-guided Visual Prompting for Enhancing Vision Transformer Performance on Unseen Domains
