princeton-nlp/semsup
Semantic Supervision: Enabling Generalization over Output Spaces
This project helps machine learning practitioners build models that can classify data into categories they've never seen before during training. You provide your data and plain-language descriptions of both familiar and new categories, and the system learns to accurately assign inputs to these novel categories. This is especially useful for researchers and developers working with image or text classification who need models to adapt to evolving datasets.
No commits in the last 6 months.
Use this if you need to train a classification model that can recognize new categories at inference time without retraining, leveraging semantic descriptions of those categories.
Not ideal if you primarily work with traditional supervised learning where all categories are known and present during training, or if you don't have descriptive text available for your categories.
Stars
16
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jan 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/princeton-nlp/semsup"
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