ybendou/ProKeR

[CVPR 2025] This repository is the official implementation of "ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models"

/ 100

Experimental

This project helps machine learning researchers efficiently adapt large vision-language models for new image classification tasks, even with very little new data. You provide a pre-trained vision-language model (like CLIP) and a small set of labeled images for your specific task, and it outputs a model that can accurately classify new images for that task. This is ideal for researchers or practitioners working on specialized image recognition problems.

No commits in the last 6 months.

Use this if you need to quickly and effectively customize a powerful existing image-text understanding model to perform a new image classification task using only a handful of examples.

Not ideal if you're looking for a general-purpose image labeling tool or if you have a large dataset for training a new model from scratch.

few-shot learning image classification vision-language models model adaptation machine learning research

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 6 / 25

Maturity 16 / 25

Community 4 / 25

How are scores calculated?

Stars

Forks

Language

Python

License

Apache-2.0

Higher-rated alternatives

oscarknagg/few-shot

Repository for few-shot learning machine learning projects

jakesnell/prototypical-networks

Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch

Implementing Siamese networks with a contrastive loss for similarity learning

google-research/meta-dataset

A dataset of datasets for learning to learn from few examples

akshaysharma096/Siamese-Networks

Few Shot Learning by Siamese Networks, using Keras.

Explore ML Frameworks

All categories Trending ML Framework directory Insights