All Projects → ShipengWang → Adam-NSCL

ShipengWang / Adam-NSCL

Licence: MIT license
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to Adam-NSCL

CVPR21 PASS
PyTorch implementation of our CVPR2021 (oral) paper "Prototype Augmentation and Self-Supervision for Incremental Learning"
Stars: ✭ 55 (+61.76%)
Mutual labels:  incremental-learning, lifelong-learning, continual-learning
FACIL
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.
Stars: ✭ 411 (+1108.82%)
Mutual labels:  incremental-learning, lifelong-learning, continual-learning
Generative Continual Learning
No description or website provided.
Stars: ✭ 51 (+50%)
Mutual labels:  incremental-learning, lifelong-learning, continual-learning
Continual Learning Data Former
A pytorch compatible data loader to create sequence of tasks for Continual Learning
Stars: ✭ 32 (-5.88%)
Mutual labels:  incremental-learning, lifelong-learning, continual-learning
cvpr clvision challenge
CVPR 2020 Continual Learning Challenge - Submit your CL algorithm today!
Stars: ✭ 57 (+67.65%)
Mutual labels:  incremental-learning, lifelong-learning, continual-learning
SIGIR2021 Conure
One Person, One Model, One World: Learning Continual User Representation without Forgetting
Stars: ✭ 23 (-32.35%)
Mutual labels:  lifelong-learning, continual-learning
CPG
Steven 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%)
Mutual labels:  lifelong-learning, continual-learning
MetaLifelongLanguage
Repository containing code for the paper "Meta-Learning with Sparse Experience Replay for Lifelong Language Learning".
Stars: ✭ 21 (-38.24%)
Mutual labels:  lifelong-learning, continual-learning
reproducible-continual-learning
Continual 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%)
Mutual labels:  lifelong-learning, continual-learning
class-norm
Class Normalization for Continual Zero-Shot Learning
Stars: ✭ 34 (+0%)
Mutual labels:  lifelong-learning, continual-learning
Remembering-for-the-Right-Reasons
Official Implementation of Remembering for the Right Reasons (ICLR 2021)
Stars: ✭ 27 (-20.59%)
Mutual labels:  lifelong-learning, continual-learning
FUSION
PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"
Stars: ✭ 18 (-47.06%)
Mutual labels:  incremental-learning, continual-learning
php-best-practices
What I consider the best practices for web and software development.
Stars: ✭ 60 (+76.47%)
Mutual labels:  continual-learning
ML-MCU
Code for IoT Journal paper title 'ML-MCU: A Framework to Train ML Classifiers on MCU-based IoT Edge Devices'
Stars: ✭ 28 (-17.65%)
Mutual labels:  incremental-learning
tornado
The Tornado 🌪️ framework, designed and implemented for adaptive online learning and data stream mining in Python.
Stars: ✭ 110 (+223.53%)
Mutual labels:  incremental-learning
continual-knowledge-learning
[ICLR 2022] Towards Continual Knowledge Learning of Language Models
Stars: ✭ 77 (+126.47%)
Mutual labels:  continual-learning
AI physicist
AI Physicist, a paradigm with algorithms for learning theories from data, by Wu and Tegmark (2019)
Stars: ✭ 23 (-32.35%)
Mutual labels:  lifelong-learning
lifelong-learning
lifelong learning: record and analysis of my knowledge structure
Stars: ✭ 18 (-47.06%)
Mutual labels:  lifelong-learning
life-disciplines-projects
Life-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%)
Mutual labels:  lifelong-learning
Train plus plus
Repo and code of the IEEE UIC paper: Train++: An Incremental ML Model Training Algorithm to Create Self-Learning IoT Devices
Stars: ✭ 17 (-50%)
Mutual labels:  incremental-learning

Adam-NSCL

This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper:

Title: Training Networks in Null Space of Feature Covariance for Continual Learning

Authors: Shipeng Wang, Xiaorong Li, Jian Sun, Zongben Xu

Email: [email protected]; [email protected]

Arxiv: https://arxiv.org/pdf/2103.07113

Usage

sh scripts_svd/adamnscl.sh

Requirements: Python 3.7, PyTorch=1.5,tensorboardX

Citation

@InProceedings{Wang_2021_CVPR,
    author    = {Wang, Shipeng and Li, Xiaorong and Sun, Jian and Xu, Zongben},
    title     = {Training Networks in Null Space of Feature Covariance for Continual Learning},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {184-193}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].