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
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.
The implementation code for Uncertainty-based Continual Learning with Adaptive Regularization (Neurips 2019)
[CVPR'22] Official Implementation of "CNLL: A Semi-supervised Approach for Continual Noisy Label Learning"
[ICPR 2022] Official Implementation of the paper "Rethinking Task-Incremental Learning Baselines" accepted in the 26th International Conference on Pattern Recognition.
Implementation of "Ternary Feature Masks: zero-forgetting for task-incremental learning"
Evaluation of Continual Relation Extraction with CL Metrics and Visualization
Implementation of Dark Experience Replay with Reservoir Sampling from scratch, benchmarked on CIL, TIL and DIL.
Production continual learning in PyTorch — three scenarios, five methods, complete benchmarks.
To associate your repository with the task-incremental-learning topic, visit your repo's landing page and select "manage topics."