nazmul-karim170/UNICON
[CVPR'22] Official Implementation of the CVPR 2022 paper "UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning"
UNICON helps machine learning researchers and practitioners build more accurate image classification models when dealing with datasets that have incorrect or "noisy" labels. It takes an image dataset with potentially inaccurate labels and outputs a robust image classification model that performs well despite the noise. This is useful for anyone working with large visual datasets, especially those sourced from the web or other uncurated collections.
No commits in the last 6 months.
Use this if your image classification model's performance is suffering because your training data contains many mislabeled examples.
Not ideal if your primary challenge is with unlabeled data or if your data quality issues are not related to noisy class labels.
Stars
63
Forks
17
Language
Python
License
MIT
Category
Last pushed
Oct 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nazmul-karim170/UNICON"
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