Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 5
평가표: 33
보존된 평가 기록: 133

Continual Learning (also known as Incremental Learning, Life-long Learning) is a concept to learn a model for a large number of tasks sequentially without forgetting knowledge obtained from the preceding tasks, where the data in the old tasks are not available anymore during training new ones.
If not mentioned, the benchmarks here are Task-CL, where task-id is provided on validation.

Source:
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Three scenarios for continual learning
Lifelong Machine Learning
Continual lifelong learning with neural networks: A review

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://bitbucket.org/catk1ns0n/repr_public

공식 코드

Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting

https://bitbucket.org/tsendeemts/metanet

공식 코드

https://github.com/1170300714/cbs

공식 코드

Class Balance Matters to Active Class-Incremental Learning

https://github.com/1170300714/lp-dif

공식 코드

Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning

https://github.com/2younis/DFGRID

공식 코드

Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data

https://github.com/2younis/dfgr

공식 코드

Data-Free Generative Replay for Class-Incremental Learning on Imbalanced Data

https://github.com/7201krap/thesis_and_experiments

공식 코드

Representations learnt by SGD and Adaptive learning rules: Conditions that vary sparsity and selectivity in neural networks

https://github.com/AKuzina/BooVAE

공식 코드

BooVAE: Boosting Approach for Continual Learning of VAE

https://github.com/AVBochkov/Embeddings

공식 코드

Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate

https://github.com/AaltoML/sfr-experiments

공식 코드

Function-space Parameterization of Neural Networks for Sequential Learning

https://github.com/AhmedFrikha/ARCADe-A-Rapid-Continual-Anomaly-Detector

공식 코드

ARCADe: A Rapid Continual Anomaly Detector

https://github.com/AlbinSou/cross_task_cil

공식 코드

On the importance of cross-task features for class-incremental learning

https://github.com/AlbinSou/lora_cl_analysis

공식 코드

An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates

https://github.com/Amgao/RLS-RTMDNet

공식 코드

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

https://github.com/AmirEstiri/Fed3Att

공식 코드

Attentive Federated Learning for Concept Drift in Distributed 5G Edge Networks

https://github.com/AndreaCossu/ContinualLearning-SequentialProcessing

공식 코드

Continual Learning with Gated Incremental Memories for sequential data processing

https://github.com/AnkurMali/ContinualPTNCN

공식 코드

Continual Learning of Recurrent Neural Networks by Locally Aligning Distributed Representations

https://github.com/AntreasAntoniou/FewShotContinualLearning

공식 코드

Defining Benchmarks for Continual Few-Shot Learning

https://github.com/AprLie/TrafficStream

공식 코드

TrafficStream: A Streaming Traffic Flow Forecasting Framework Based on Graph Neural Networks and Continual Learning

https://github.com/B-Deprez/BeGin

공식 코드

Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Review

https://github.com/BerenMillidge/theoretical_framework_predictive_coding

공식 코드

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

https://github.com/BoSmallEar/COOLer

공식 코드

COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking

https://github.com/Brain-Cog-Lab/IEMF

공식 코드

Incorporating brain-inspired mechanisms for multimodal learning in artificial intelligence

https://github.com/CZSLwithCVAE/CZSL_CVAE

공식 코드

Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)

https://github.com/CameronTaylorFL/stam

공식 코드

Unsupervised Progressive Learning and the STAM Architecture

https://github.com/CameronTaylorFL/upl-benchmark

공식 코드

Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning

https://github.com/ChristosKap/multi_timescale_replay

공식 코드

Continual Reinforcement Learning with Multi-Timescale Replay

https://github.com/ContinualAI/avalanche

공식 코드

Avalanche: an End-to-End Library for Continual Learning

https://github.com/Continvvm/continuum

공식 코드

Continuum: Simple Management of Complex Continual Learning Scenarios

https://github.com/Coral79/CDDB

공식 코드

A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials

https://github.com/CyanML/FTF-ER

공식 코드

FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning

https://github.com/DVAEsCL/DVAEsCL

공식 코드

Shared and Private VAEs with Generative Replay for Continual Learning

https://github.com/DVGR-CZSL/DVGR-CZSL

공식 코드

Dynamic VAEs with Generative Replay for Continual Zero-shot Learning

https://github.com/DanWaxman/OnlineBayesianStacking

공식 코드

Bayesian Ensembling: Insights from Online Optimization and Empirical Bayes

https://github.com/DannyFGitHub/COVID-19PneumoCheckApp

공식 코드

From Lab to Pocket: A Novel Continual Learning-based Mobile Application for Screening COVID-19

https://github.com/Debatrix/UPCL

공식 코드

Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspective

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.