incremental-learning

🌊 Online machine learning in Python

Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel XPU (CPU-only and CUDA also supported).

PyCIL: A Python Toolbox for Class-Incremental Learning

(CVPR 2021 Oral) Open World Object Detection

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

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.

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).

TPAMI 2026 | This repository collects awesome survey, resource, and paper for lifelong learning LLM agents

Streaming anomaly detection in Python: 16 online detectors (xStream, LODA, RS-Hash, Half-Space Trees, RRCF…) plus calibration and prequential evaluation for real-time 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).

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

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.

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

CapyMOA does efficient machine learning for data streams in Python. CapyMOA is a toolbox of methods and evaluators for: classification, regression, clustering, anomaly detection, semi-supervised learning, online continual learning, and drift detection for data streams.

(TPAMI 2021) iOD: Incremental Object Detection via Meta-Learning

Online anomaly detection for data streams/ Real-time anomaly detection for time series data.