chengtan9907/Co-learning
The official implementation of the ACM MM'21 paper Co-learning: Learning from noisy labels with self-supervision.
This project helps machine learning researchers and practitioners train more accurate image classification models when their training datasets contain mislabeled examples. It takes your image dataset with potentially incorrect labels and applies advanced algorithms to filter out the noise, resulting in a more robust and reliable classification model. It's ideal for those working on image recognition tasks where perfect data labeling is challenging or expensive.
122 stars. No commits in the last 6 months.
Use this if you are developing image classification models and suspect or know that your training data has a significant number of incorrect labels.
Not ideal if your datasets are perfectly clean and accurately labeled, or if you are not working with image data.
Stars
122
Forks
13
Language
Python
License
—
Category
Last pushed
May 17, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chengtan9907/Co-learning"
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