mashijie1028/ProtoGCD
(TPAMI 2025) ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery
This project helps machine learning researchers improve how their image classification models identify new, unlabeled categories within datasets, even when some categories are already known. It takes in image datasets, some with known labels and some entirely unknown, and outputs a more robust model that can accurately discover and categorize these novel images. This is primarily for computer vision and machine learning researchers developing advanced classification systems.
No commits in the last 6 months.
Use this if you are a researcher working on image classification and need to automatically identify and group entirely new categories of images within a dataset, alongside existing known categories.
Not ideal if you are an end-user looking for a pre-built tool for standard image classification tasks with fully labeled data.
Stars
34
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jun 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mashijie1028/ProtoGCD"
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