Aug 2026
Adapting Vision Foundation Models with Cascaded Semantics
This work injects two complementary semantic priors into Visual prompt tuning, a cascaded scheme that integrates both priors throughout ViT adaptation, and proposes a cascaded scheme that integrates both priors throughout ViT adaptation.
Xianye Xiao, Xingjian Li, Cheng Han et al.
· Trans. Mach. Learn. Res. · 0 citations