Skip to content
#

icarl

Here are 16 public repositories matching this topic...

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

  • Updated Nov 5, 2025
  • Jupyter Notebook

Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning methods and 4 baselines. Official Codebase of "A continual learning survey: Defying forgetting in classification tasks." in IEEE TPAMI.

  • Updated Jun 3, 2021
  • Python

A replay-based continual learning, where models preserve past knowledge through stored exemplars or pseudo-samples. Implements Experience Replay (ER), Gradient Episodic Memory (GEM), and iCaRL. Provides modular dataset buffering, memory selection policies, and evaluation utilities for reproducible experiments on vision and NLP tasks.

  • Updated Oct 15, 2025
  • Python

Add this topic to your repo

To associate your repository with the icarl topic, visit your repo's landing page and select "manage topics."

Learn more