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/bkvogel/pfc

공식 코드

An NMF-Based Building Block for Interpretable Neural Networks With Continual Learning

https://github.com/blackblitz/bcl

공식 코드

On Sequential Loss Approximation for Continual Learning

https://github.com/bladedancer957/cpfd

공식 코드

Continual Named Entity Recognition without Catastrophic Forgetting

https://github.com/bmazoure/DRIML

공식 코드

Deep Reinforcement and InfoMax Learning

https://github.com/bokun-wang/moml

공식 코드

Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning

https://github.com/boluoweifenda/WAGE

공식 코드

Training and Inference with Integers in Deep Neural Networks

https://github.com/boschresearch/mocl-naacl-2024

공식 코드

Rehearsal-Free Modular and Compositional Continual Learning for Language Models

https://github.com/bowang-rw-02/scl-one-for-four

공식 코드

One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning

https://github.com/braincog-x/brain-cog

공식 코드

Enhancing Efficient Continual Learning with Dynamic Structure Development of Spiking Neural Networks

https://github.com/burakgurbuz97/nispa

공식 코드

NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks

https://github.com/burakgurbuz97/sharp-continual-learning

공식 코드

SHARP: Sparsity and Hidden Activation RePlay for Neuro-Inspired Continual Learning

https://github.com/bwnzheng/lpa_icme2023

공식 코드

Preserving Locality in Vision Transformers for Class Incremental Learning

https://github.com/bwnzheng/tagfex_cvpr2025

공식 코드

Task-Agnostic Guided Feature Expansion for Class-Incremental Learning

https://github.com/bytefuse/mamlcon

공식 코드

Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learning

https://github.com/byyx666/ACL_code

공식 코드

Adapt before Continual Learning

https://github.com/byyx666/Dual-Arch

공식 코드

Rethinking the Stability-Plasticity Trade-off in Continual Learning from an Architectural Perspective

https://github.com/byyx666/archcraft

공식 코드

Revisiting Neural Networks for Continual Learning: An Architectural Perspective

https://github.com/caicch/colpro

공식 코드

Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting

https://github.com/cambridge-mlg/cnaps

공식 코드

Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes

https://github.com/canpeng123/fscil_alice

공식 코드

Few-Shot Class-Incremental Learning from an Open-Set Perspective

https://github.com/cardiffnlp/timelms

공식 코드

TimeLMs: Diachronic Language Models from Twitter

https://github.com/cc13qq/cad

공식 코드

Continual Adversarial Defense

https://github.com/ccc-frankfurt/DP-NAS

공식 코드

Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference

https://github.com/ccc-frankfurt/EndlessCL-Simulator-Source

공식 코드

A Procedural World Generation Framework for Systematic Evaluation of Continual Learning

https://github.com/cdjkim/PRS

공식 코드

Imbalanced Continual Learning with Partitioning Reservoir Sampling

https://github.com/cea-list/metamtreg

공식 코드

Improving Few-Shot Learning through Multi-task Representation Learning Theory

https://github.com/cecile-hi/regularized-adaptive-weight-modification

공식 코드

Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection

https://github.com/cerenaut/cfsl

공식 코드

Expanding continual few-shot learning benchmarks to include recognition of specific instances

https://github.com/cerenaut/wmar

공식 코드

Augmenting Replay in World Models for Continual Reinforcement Learning

https://github.com/chan-li/vcl

공식 코드

Statistical mechanics of continual learning: variational principle and mean-field potential

https://github.com/chandar-lab/CMAL_Hanabi

공식 코드

Continuous Coordination As a Realistic Scenario for Lifelong Learning

https://github.com/chandar-lab/Lifelong-Hanabi

공식 코드

Continuous Coordination As a Realistic Scenario for Lifelong Learning

https://github.com/chaoqi7/bsa-cil-3d

공식 코드

Boosting the Class-Incremental Learning in 3D Point Clouds via Zero-Collection-Cost Basic Shape Pre-Training

https://github.com/chaoqi7/cmip-cil

공식 코드

CMIP-CIL: A Cross-Modal Benchmark for Image-Point Class Incremental Learning

https://github.com/charleshsc/CompoFormer

공식 코드

Continual Task Learning through Adaptive Policy Self-Composition

https://github.com/chasonjiang/fscilss

공식 코드

Few-shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation

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