townim-faisal/FSCIL-3D
[ECCV 2022] Few-shot class incremental learning on 3D point clouid objects
This helps researchers and engineers in computer vision to train AI models that can incrementally learn to recognize new 3D objects from very few examples. It takes existing 3D point cloud data and new, limited 3D point cloud examples, and outputs an updated model capable of classifying an expanded range of 3D objects. This is primarily for machine learning practitioners working with 3D object recognition.
No commits in the last 6 months.
Use this if you need to continuously update a 3D object recognition system to identify new objects without retraining on all past data, especially when new data is scarce and comes from different real-world sources.
Not ideal if you are looking for an out-of-the-box solution for general 3D object detection or if you don't have experience with machine learning model training.
Stars
32
Forks
6
Language
Python
License
—
Category
Last pushed
Jan 16, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/townim-faisal/FSCIL-3D"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
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"