rehg-lab/lowshot-shapebias
Learning low-shot object classification with explicit shape bias learned from point clouds
This project helps computer vision researchers categorize 3D objects more accurately, especially when they have very few examples for a new object type. It takes 3D point cloud data or images of objects and outputs better classifications by focusing on the object's shape. This is ideal for researchers developing new object recognition systems that need to learn from limited data.
No commits in the last 6 months.
Use this if you are a computer vision researcher working on object classification and need to improve accuracy when you have only a few examples of new object categories.
Not ideal if you are looking for a general-purpose, off-the-shelf solution for image classification without specific interest in low-shot learning or 3D shape analysis.
Stars
55
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 08, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rehg-lab/lowshot-shapebias"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
Sha-Lab/FEAT
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"