NJUyued/PRG4SSL-MNAR
"Towards Semi-supervised Learning with Non-random Missing Labels" by Yue Duan (ICCV 2023)
This project helps machine learning engineers improve the accuracy of semi-supervised image classification models. It takes in datasets where a small portion of images are labeled, and those labels are unevenly distributed across different categories. The output is a more robust image classification model that performs better even when dealing with real-world datasets where some categories are rare.
Use this if you are developing computer vision models and need to effectively train them using a mix of labeled and unlabeled image data, especially when the labeled examples disproportionately represent certain classes.
Not ideal if your image datasets are fully labeled or if the missing labels are randomly distributed across all categories.
Stars
77
Forks
1
Language
Python
License
—
Category
Last pushed
Nov 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NJUyued/PRG4SSL-MNAR"
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