JosephKJ/Awesome-Novel-Class-Discovery
A list of papers that studies Novel Class Discovery
This is a curated list of research papers and preprints focused on Novel Class Discovery (NCD), a machine learning problem where new, previously unseen categories are identified from unlabelled data, even when some labelled data from other categories is available. It helps machine learning researchers stay updated on the latest advancements and different problem settings within NCD. The resource provides direct links to papers and their associated code for further exploration.
515 stars.
Use this if you are a machine learning researcher or practitioner interested in discovering new data categories automatically, particularly when you already have some labelled data for known categories.
Not ideal if you are looking for an off-the-shelf software tool to directly apply Novel Class Discovery, as this is a list of research papers, not an implementation.
Stars
515
Forks
63
Language
—
License
—
Category
Last pushed
Feb 15, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JosephKJ/Awesome-Novel-Class-Discovery"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ntucllab/libact
Pool-based active learning in Python
scikit-activeml/scikit-activeml
scikit-activeml: A Comprehensive and User-friendly Active Learning Library
python-adaptive/adaptive
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions
NUAA-AL/ALiPy
ALiPy: Active Learning in Python is an active learning python toolbox, which allows users to...
ai4co/awesome-fm4co
Recent research papers about Foundation Models for Combinatorial Optimization