nayeemrizve/TRSSL
"Towards Realistic Semi-Supervised Learning" by Mamshad Nayeem Rizve, Navid Kardan, Mubarak Shah (ECCV 2022)
This project helps machine learning engineers and researchers classify images, especially when they have a limited number of labeled examples but many unlabeled ones. It takes in a mix of labeled and unlabeled images, even if some unlabeled images contain entirely new categories, and outputs highly accurate classification models. This is ideal for those building computer vision systems where annotating all data is too costly or impractical.
No commits in the last 6 months.
Use this if you need to train a robust image classification model with an incomplete dataset where some classes are labeled, but many others (including potentially unknown ones) are not.
Not ideal if your dataset is fully labeled and balanced, or if you are not working with image classification tasks.
Stars
41
Forks
4
Language
Python
License
MIT
Category
Last pushed
Mar 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nayeemrizve/TRSSL"
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