dahyun-kang/ifsl
[CVPR'22] Official PyTorch implementation of Integrative Few-Shot Learning for Classification and Segmentation
This project helps computer vision researchers and practitioners classify and segment objects in images, even when very few examples of those objects are available for training. You provide a small set of labeled images, and the system outputs a model that can identify and outline those objects in new images. It is used by professionals working with image analysis, particularly in fields where data labeling is expensive or scarce.
133 stars. No commits in the last 6 months.
Use this if you need to perform image classification or segmentation for categories with extremely limited training data.
Not ideal if you have abundant labeled data, as more traditional deep learning methods might be more straightforward to implement.
Stars
133
Forks
18
Language
Python
License
MIT
Category
Last pushed
Jan 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dahyun-kang/ifsl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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.