lancopku/well-classified-examples-are-underestimated
Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"
This project provides an alternative way to train deep neural networks for classification tasks. It takes your existing deep learning model and training data, and by adjusting how 'well-classified' examples contribute to the learning process, it aims to produce a more robust and accurate classification model. This is for machine learning researchers and practitioners who are developing and optimizing deep neural networks.
No commits in the last 6 months.
Use this if you are training deep neural networks for classification and want to explore a method to improve model representations, energy optimization, and margin growth beyond standard cross-entropy loss.
Not ideal if you are looking for a pre-trained model, a no-code solution, or are not working directly with deep learning model training and loss functions.
Stars
54
Forks
2
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Sep 19, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lancopku/well-classified-examples-are-underestimated"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Trusted-AI/adversarial-robustness-toolbox
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion,...
bethgelab/foolbox
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
cleverhans-lab/cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
DSE-MSU/DeepRobust
A pytorch adversarial library for attack and defense methods on images and graphs
BorealisAI/advertorch
A Toolbox for Adversarial Robustness Research