5 papers
Class Adaptive Conformal Training
Badr-Eddine Marani, Julio Silva-Rodriguez, Ismail Ben Ayed +3
Deep neural networks have achieved remarkable success across a variety of tasks, yet they often suffer from unreliable probability estimates. As a result, they can be overconfident…
Semantic Anchor Transport: Robust Test-Time Adaptation for Vision-Language Models
Shambhavi Mishra, Julio Silva-Rodriguez, Ismail Ben Ayed +2
Large pre-trained vision-language models (VLMs), such as CLIP, have shown unprecedented zero-shot performance across a wide range of tasks. Nevertheless, these models may be unreli…
Trustworthy Few-Shot Transfer of Medical VLMs through Split Conformal Prediction
Julio Silva-RodrÃguez, Ismail Ben Ayed, Jose Dolz
Medical vision-language models (VLMs) have demonstrated unprecedented transfer capabilities and are being increasingly adopted for data-efficient image classification. Despite its…
Few-Shot, Now for Real: Medical VLMs Adaptation without Balanced Sets or Validation
Julio Silva-RodrÃguez, Fereshteh Shakeri, Houda Bahig +2
Vision-language models (VLMs) are gaining attention in medical image analysis. These are pre-trained on large, heterogeneous data sources, yielding rich and transferable representa…
A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision
Julio Silva-RodrÃguez, Hadi Chakor, Riadh Kobbi +2
Foundation vision-language models are currently transforming computer vision, and are on the rise in medical imaging fueled by their very promising generalization capabilities. How…