MaxZanella

CLIP-LoRA. An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].

MTA. [CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentation (MTA).

StatA. [CVPR 2025 - Highlight] Official implementation of the paper "Realistic Test-Time Adaptation of Vision-Language Models" (StatA).

transduction-for-vlms. [NeurIPS 2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with Transduction".

vocabulary-free-FSL. [CVPRW 2025] Official implementation of the paper "Vocabulary-free few-shot learning for Vision-Language Models".

WSBIM2243---Mammography-processing. We present methods to preprocess, detect tumours and segment malignant masses for the INbreast dataset.

WSBIM2243. Traitement d'images médicales dans le cadre du cours WSBIM2243