sung-yeon-kim/HIER-CVPR23
Official PyTorch Implementation of HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization, CVPR 2023
This project helps improve the performance of image recognition systems by understanding the subtle relationships between different image categories. It takes a collection of labeled images as input and produces an 'embedding space' where similar images are grouped more closely, even if they belong to different, but related, classes. This is useful for anyone building or evaluating visual search, recommendation, or classification systems.
No commits in the last 6 months.
Use this if you need to build more robust image search or recommendation systems that can recognize nuanced similarities beyond simple category labels.
Not ideal if you are looking for a ready-to-use application rather than a deep learning training framework.
Stars
66
Forks
6
Language
Python
License
MIT
Category
Last pushed
Sep 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sung-yeon-kim/HIER-CVPR23"
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.