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://github.com/machado-research/AgarCL

공식 코드

The Cell Must Go On: Agar.io for Continual Reinforcement Learning

https://github.com/machinelearningbcam/imrcs-for-incremental-learning-neurips-2023

공식 코드

Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

https://github.com/machinelearningbcam/supervised-learning-evolving-task-jmlr-2024

공식 코드

Supervised Learning with Evolving Tasks and Performance Guarantees

https://github.com/machinelearningbcam/supervised-learning-evolving-task-jmlr-2025

공식 코드

Supervised Learning with Evolving Tasks and Performance Guarantees

https://github.com/mahdiyarmm/continual-pedestrian-detection

공식 코드

Continual Learning for Out-of-Distribution Pedestrian Detection

https://github.com/mahsapaknezhad/part

공식 코드

PaRT: Parallel Learning Towards Robust and Transparent AI

https://github.com/mail-research/sbl-resilient-backdoors

공식 코드

Flatness-aware Sequential Learning Generates Resilient Backdoors

https://github.com/mala-lab/opencil

공식 코드

OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learning

https://github.com/mala-lab/tpp

공식 코드

Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach

https://github.com/malwarereplaygan/malcl

공식 코드

MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification

https://github.com/manoja328/rodeo

공식 코드

RODEO: Replay for Online Object Detection

https://github.com/maolinluo/lada

공식 코드

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning

https://github.com/maorong-wang/ccl-dc

공식 코드

Improving Plasticity in Online Continual Learning via Collaborative Learning

https://github.com/maorong-wang/esrm

공식 코드

Dealing with Synthetic Data Contamination in Online Continual Learning

https://github.com/mapolinario94/CODE-CL

공식 코드

CODE-CL: Conceptor-Based Gradient Projection for Deep Continual Learning

https://github.com/marcusklasson/replay_scheduling

공식 코드

Learn the Time to Learn: Replay Scheduling in Continual Learning

https://github.com/mariacer/cl_in_rnns

공식 코드

Continual Learning in Recurrent Neural Networks

https://github.com/martinbarry59/gateonmnist

공식 코드

Context selectivity with dynamic availability enables lifelong continual learning

https://github.com/masuyama-lab/cae

공식 코드

A Parameter-free Adaptive Resonance Theory-based Topological Clustering Algorithm Capable of Continual Learning

https://github.com/masuyama-lab/caeac

공식 코드

Class-wise Classifier Design Capable of Continual Learning using Adaptive Resonance Theory-based Topological Clustering

https://github.com/masuyama-lab/mlca

공식 코드

Multi-label Classification via Adaptive Resonance Theory-based Clustering

https://github.com/mateusz-wojcik-97/domain-agnostic-architecture

공식 코드

Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform

https://github.com/mateusz-wojcik-97/neural-architecture-for-online-ensemble-cl

공식 코드

Neural Architecture for Online Ensemble Continual Learning

https://github.com/mattdl/DUA

공식 코드

Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem

https://github.com/mattdl/continualevaluation

공식 코드

Continual evaluation for lifelong learning: Identifying the stability gap

https://github.com/mattiafanan/cl-driveridentification

공식 코드

Continual Learning for Behavior-based Driver Identification

https://github.com/mattriemer/mer

공식 코드

Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference

https://github.com/mayyoy/rppgdil

공식 코드

Continual Learning for Remote Physiological Measurement: Minimize Forgetting and Simplify Inference

https://github.com/mbosc/twf

공식 코드

Transfer without Forgetting

https://github.com/mccaffary/continual-learning

공식 코드

Towards continual task learning in artificial neural networks: current approaches and insights from neuroscience

https://github.com/meclabtuda/atlas-replay

공식 코드

Continual atlas-based segmentation of prostate MRI

https://github.com/meryemmhamdi1/x-continuous-learning

공식 코드

Cross-lingual Lifelong Learning

https://github.com/michalzajac-ml/pec

공식 코드

Prediction Error-based Classification for Class-Incremental Learning

https://github.com/michigan-traffic-lab/DECODE

공식 코드

DECODE: Domain-aware Continual Domain Expansion for Motion Prediction

https://github.com/microsoft/simulated-trial-and-error

공식 코드

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error

https://github.com/miladkhademinori/class-incremental-learning

공식 코드

Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings

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