mlbio-epfl/turtle
[ICML 2024] Let Go of Your Labels with Unsupervised Transfer
TURTLE helps machine learning practitioners automatically categorize data without needing human-labeled examples. It takes image or text data as input, leverages existing powerful 'foundation models' to understand the data, and outputs a clear, underlying categorization. This is ideal for researchers or data scientists working with large, unlabeled datasets.
Use this if you need to classify visual or textual data into distinct categories, but lack the extensive human-labeled datasets typically required for training machine learning models.
Not ideal if you already have a well-labeled dataset for your specific task, as supervised learning methods might offer more direct control and potentially higher accuracy for known labels.
Stars
80
Forks
7
Language
Python
License
—
Category
Last pushed
Dec 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mlbio-epfl/turtle"
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