nazmul-karim170/CNLL
[CVPR'22] Official Implementation of "CNLL: A Semi-supervised Approach for Continual Noisy Label Learning"
This project helps machine learning researchers evaluate and improve their image classification models. It takes an existing image dataset with potentially inaccurate labels and continuously trains the model while simultaneously identifying and correcting these noisy labels over time. The primary users are researchers or engineers working on robust computer vision systems.
No commits in the last 6 months.
Use this if you are a researcher or engineer developing image classification models and need a method to train effectively with noisy or evolving label data.
Not ideal if you are a practitioner looking for a ready-to-use image classification model or a general-purpose data cleaning tool outside of academic computer vision research.
Stars
18
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nazmul-karim170/CNLL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aimagelab/mammoth
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of...
LAMDA-CL/PyCIL
PyCIL: A Python Toolbox for Class-Incremental Learning
GMvandeVen/continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR,...
LAMDA-CL/LAMDA-PILOT
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
mmasana/FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.