nayeemrizve/OpenLDN
"OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning" by Mamshad Nayeem Rizve, Navid Kardan, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah (ECCV 2022)
This project helps machine learning practitioners automatically identify and categorize previously unknown types of data alongside known ones. You provide a small set of labeled examples for known categories and a large pool of unlabeled data, which may contain both known and entirely new categories. The output is a system that can accurately classify known items and group novel items into distinct new categories. This is ideal for data scientists or AI engineers working with evolving datasets.
No commits in the last 6 months.
Use this if you need to build a robust classification system where new, unseen categories of data might appear in your unlabeled dataset, and you want to detect and cluster them automatically.
Not ideal if all your unlabeled data is guaranteed to belong to categories you have already explicitly labeled.
Stars
36
Forks
3
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/OpenLDN"
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