incremental-learning

🌊 Online machine learning in Python

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.

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

(CVPR 2021 Oral) Open World Object Detection

PyCIL: A Python Toolbox for Class-Incremental Learning

An Incremental Learning, Continual Learning, and Life-Long Learning Repository

Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.

Evaluate three types of task shifting with popular continual learning algorithms.

🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox

A clean and simple data loading library for Continual Learning

A collection of online continual learning paper implementations and tricks for computer vision in PyTorch, including our ASER(AAAI-21), SCR(CVPR21-W) and survey (Neurocomputing).

A collection of incremental learning paper implementations including PODNet (ECCV20) and Ghost (CVPR-W21).

The efficient SMT-based context-bounded model checker (ESBMC)

Streaming Anomaly Detection Framework in Python (Outlier Detection for Streaming Data)

A brain-inspired version of generative replay for continual learning with deep neural networks (e.g., class-incremental learning on CIFAR-100; PyTorch code).

This repository collects awesome survey, resource, and paper for lifelong learning LLM agents

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.

PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need (IJCV 2024)