In this codebase we establish a benchmark for egocentric user adaptation based on Ego4d.First, we start from a population model which has data from many users to learn user-agnostic representations…

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.

[Spotlight ICLR 2023 paper] Continual evaluation for lifelong learning with neural networks, identifying the stability gap.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

HiPlot makes understanding high dimensional data easy

CVPR 2022 Continual Learning in Computer Vision Workshop Challenge

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

Multi-Joint dynamics with Contact. A general purpose physics simulator.

A toolkit for reproducible reinforcement learning research.

Reinforcement learning resources curated

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

Avalanche fork adding RL support

Awesome resources on normalizing flows.

🌊 Online machine learning in Python

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

BlockCopy (ICCV2021) implementation in PyTorch, accelerating neural networks with block-sparse execution

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

A Neuromodulated Meta-Learning algorithm

Continual Learning papers list, curated by ContinualAI

PyTorch implementation of AANets (CVPR 2021) and Mnemonics Training (CVPR 2020 Oral)

Tensors and Dynamic neural networks in Python with strong GPU acceleration

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Paper bank for Self-Supervised Learning