stypoumic/BECLR
Official repository for the paper BECLR: Batch Enhanced Contrastive Unsupervised Few-Shot Learning
This project helps machine learning practitioners classify new images quickly and accurately, even with very few examples for each new category. You input a large collection of unlabeled images for pre-training and then a tiny handful of labeled images for new categories. The output is a highly effective image classification model ready to identify new, unseen images from those categories. This is ideal for AI/ML researchers and data scientists working with image recognition tasks where labeled data is scarce.
No commits in the last 6 months.
Use this if you need to build robust image classification models for new categories but have very limited labeled data available.
Not ideal if you have abundant labeled data for all your image categories or if your primary need is not few-shot learning.
Stars
16
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stypoumic/BECLR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification