AI RESEARCH
Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning
arXiv CS.CV
•
ArXi:2604.12403v1 Announce Type: new Test-Time Prompt Tuning (TPT) adapts vision-language models using augmented views, but its effectiveness is hindered by the challenge of determining which views are beneficial. Standard entropy-based filtering relies on the internal confidence scores of the model, which are often miscalibrated under distribution shift, assigning high confidence to irrelevant crops or background regions while ignoring semantic content. To address this, we propose a dual-modality anchor-guided framework that grounds view selection in semantic evidence. We.