TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a purely training-free few-shot adaptation method for Medical VLMs, which is fast and model-agnostic. TCLA corrects inference logits based on a small set
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 57%vlm-starter →
- LinkedLinked via arxiv author · 85%Tianyou Jiang →
“TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models”
- LinkedLinked via arxiv author · 85%Ziyu Zhou →
“TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models”