Pinned Repositories
MTA
[CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentation (MTA).
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].
transduction-for-vlms
[NeurIPS2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with Transduction".
RS-TransCLIP
Open-source code for the paper "Enhancing Remote Sensing Vision-Language Models for Zero-Shot Scene Classification"
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
Active-Learning-for-Mammography
This repository includes the Active Learning strategies assessed in the Master Thesis: Deep Learning in Mammography realized Maxime Zanella and supervised by Professor Benoit Macq at UCLouvain.
CoOp
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
darknet
Convolutional Neural Networks
invertible-resnet
Official Code for Invertible Residual Networks
MaxZanella's Repositories
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].
MaxZanella/transduction-for-vlms
[NeurIPS2024 - Spotlight] Transduction for Vision-Language Models (TransCLIP): code for the paper "Boosting Vision-Language Models with Transduction".
MaxZanella/MTA
[CVPR 2024] Zero-shot method for Vision-Language Models based on a robust formulation of the MeanShift algorithm for Test-time Augmentation (MTA).
MaxZanella/test_page
MaxZanella/Tip-Adapter
MaxZanella/invertible-resnet
Official Code for Invertible Residual Networks
MaxZanella/CoOp
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
MaxZanella/Active-Learning-for-Mammography
This repository includes the Active Learning strategies assessed in the Master Thesis: Deep Learning in Mammography realized Maxime Zanella and supervised by Professor Benoit Macq at UCLouvain.
MaxZanella/WSBIM2243---Mammography-processing
We present methods to preprocess, detect tumours and segment malignant masses for the INbreast dataset.
MaxZanella/WSBIM2243
Traitement d'images médicales dans le cadre du cours WSBIM2243
MaxZanella/darknet
Convolutional Neural Networks
MaxZanella/project_git
MaxZanella/pytorch-a2c
A well-documented A2C written in PyTorch
MaxZanella/SystInfo