luoyan407 / grad_prediction

[TNNLS 2024] Learning to Predict Gradients for Semi-Supervised Continual Learning

Learning to Predict Gradients for Semi-Supervised Continual Learning

Code for project: "Learning to Predict Gradients for Semi-Supervised Continual Learning".

Requirements and Environment

• Main dependency: PyTorch 1.4.0+
• The code is tested under Ubuntu 1804 LTS with Python 3.7.

Tasks for Evaluation

Continual Learning

The code and script that run experiments on MNIST-R, MNIST-P, and iCIFAR-100 are in folder continual.

Adversarial Continual Learning

The code and script that run experiments on CIFAR-100 and MiniImageNet are in folder adversarial_continual.