FACILFramework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.
Stars: ✭ 411 (+1108.82%)
cvpr clvision challengeCVPR 2020 Continual Learning Challenge - Submit your CL algorithm today!
Stars: ✭ 57 (+67.65%)
CVPR21 PASSPyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"
Stars: ✭ 55 (+61.76%)
FUSIONPyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"
Stars: ✭ 18 (-47.06%)
class-normClass Normalization for Continual Zero-Shot Learning
Stars: ✭ 34 (+0%)
SIGIR2021 ConureOne Person, One Model, One World: Learning Continual User Representation without Forgetting
Stars: ✭ 23 (-32.35%)
CPGSteven C. Y. Hung, Cheng-Hao Tu, Cheng-En Wu, Chien-Hung Chen, Yi-Ming Chan, and Chu-Song Chen, "Compacting, Picking and Growing for Unforgetting Continual Learning," Thirty-third Conference on Neural Information Processing Systems, NeurIPS 2019
Stars: ✭ 91 (+167.65%)
MetaLifelongLanguageRepository containing code for the paper "Meta-Learning with Sparse Experience Replay for Lifelong Language Learning".
Stars: ✭ 21 (-38.24%)
reproducible-continual-learningContinual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.
Stars: ✭ 118 (+247.06%)
incremental trainingRepo that relates to the Medium blog 'Keeping your ML model in shape with Kafka, Airflow' and MLFlow'
Stars: ✭ 110 (+223.53%)
tornadoThe Tornado 🌪️ framework, designed and implemented for adaptive online learning and data stream mining in Python.
Stars: ✭ 110 (+223.53%)
life-disciplines-projectsLife-Disciplines-Projects (LDP) is a life-management framework built within Obsidian. Feel free to transform it for your own personal needs.
Stars: ✭ 130 (+282.35%)
php-best-practicesWhat I consider the best practices for web and software development.
Stars: ✭ 60 (+76.47%)
River🌊 Online machine learning in Python
Stars: ✭ 2,980 (+8664.71%)
Train plus plusRepo and code of the IEEE UIC paper: Train++: An Incremental ML Model Training Algorithm to Create Self-Learning IoT Devices
Stars: ✭ 17 (-50%)
cvaecaposrCode for the Paper: "Conditional Variational Capsule Network for Open Set Recognition", Y. Guo, G. Camporese, W. Yang, A. Sperduti, L. Ballan, arXiv:2104.09159, 2021.
Stars: ✭ 29 (-14.71%)
ML-MCUCode for IoT Journal paper title 'ML-MCU: A Framework to Train ML Classifiers on MCU-based IoT Edge Devices'
Stars: ✭ 28 (-17.65%)
AI physicistAI Physicist, a paradigm with algorithms for learning theories from data, by Wu and Tegmark (2019)
Stars: ✭ 23 (-32.35%)
lifelong-learninglifelong learning: record and analysis of my knowledge structure
Stars: ✭ 18 (-47.06%)
HebbianMetaLearningMeta-Learning through Hebbian Plasticity in Random Networks: https://arxiv.org/abs/2007.02686
Stars: ✭ 77 (+126.47%)
AirLoopAirLoop: Lifelong Loop Closure Detection
Stars: ✭ 49 (+44.12%)
class-incremental-learningPyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).
Stars: ✭ 30 (-11.76%)
GPMOfficial Code Repository for "Gradient Projection Memory for Continual Learning"
Stars: ✭ 50 (+47.06%)
CVPR2021 PLOPOfficial code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation
Stars: ✭ 102 (+200%)
BLIPOfficial Implementation of CVPR2021 paper: Continual Learning via Bit-Level Information Preserving
Stars: ✭ 33 (-2.94%)
OCDVAEContinualLearningOpen-source code for our paper: Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
Stars: ✭ 56 (+64.71%)
ADER(RecSys 2020) Adaptively Distilled Exemplar Replay towards Continual Learning for Session-based Recommendation [Best Short Paper]
Stars: ✭ 28 (-17.65%)