Conference
Open access
Sep 2026
MLDA: Test-Time Multi-Level Adaptation with Dynamic Alignment for Compositional Zero-Shot Learning
MLDA is introduced, a test-time adaptation framework for CZSL that jointly derives multi-level prototypes and performs dynamic vision–language alignment and leverages optimal transport to achieve consistent matching of semantically salient information across modalities.
Miao-Ge Li, Yu Liu, Jingcai Guo
· Proceedings of the Thirty-Fi... · 0 citations