Medical vision-language models perform well in zero-shot settings but degrade when applied to new imaging domains due to distribution shifts and class imbalance from pretraining. This paper introduces a training-free method that adjusts inference logits using only a handful of support examples, improving class separation without adding trainable components - important since low-data regimes (like one-shot) are often unstable for existing adaptation techniques. Tested across nine datasets spanning X-ray, ultrasound, MRI, CT, and histopathology, it outperforms most training-based alternatives. Applications include rapid, lightweight adaptation of medical AI diagnostic tools across imaging modalities and hospital settings with minimal labeled data.
Podden och tillhörande omslagsbild på den här sidan tillhör
Craig Spencer Smith. Innehållet i podden är skapat av Craig Spencer Smith och inte av,
eller tillsammans med, Poddtoppen.
