Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment
Test-time adaptation (TTA) has emerged as a key strategy to enhance vision-language models (VLMs) under real-world distribution changes. However, existing methods always face two problems: 1) The fundamental trade-off dilemma: parameter-free TTA retains inference efficiency but fails to correct modality misalignment, w...