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/wjmacro/continualmt

공식 코드

F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation

https://github.com/wkddydpf/continual-knowledge-learning

공식 코드

Towards Continual Knowledge Learning of Language Models

https://github.com/wojciechl02/stability-gap-nmc

공식 코드

Exploring the Stability Gap in Continual Learning: The Role of the Classification Head

https://github.com/wonseok1017/nn-rfr

공식 코드

Improving Forward Compatibility in Class Incremental Learning by Increasing Representation Rank and Feature Richness

https://github.com/wqza/cba-online-cl

공식 코드

CBA: Improving Online Continual Learning via Continual Bias Adaptor

https://github.com/wsqwsq/Towards-a-Defense-against-Backdoor-Attacks-in-Continual-Federated-Learning

공식 코드

Towards a Defense Against Federated Backdoor Attacks Under Continuous Training

https://github.com/wx-zhang/continual-learning-on-a-diet

공식 코드

Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation

https://github.com/wx-zhang/spu

공식 코드

Overcoming Generic Knowledge Loss with Selective Parameter Update

https://github.com/wxr99/Forgetting-Ignorance-or-Myopia-Revisiting-Key-Challenges-in-Online-Continual-Learning

공식 코드

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning

https://github.com/wxr99/cut-replay

공식 코드

Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning

https://github.com/wyjeong/FedWeIT

공식 코드

Federated Continual Learning with Weighted Inter-client Transfer

https://github.com/xduan7/hat-cl

공식 코드

HAT-CL: A Hard-Attention-to-the-Task PyTorch Library for Continual Learning

https://github.com/xfflzl/cim-cil

공식 코드

Class-Incremental Exemplar Compression for Class-Incremental Learning

https://github.com/xialeiliu/Awesome-Incremental-Learning

공식 코드

The Ideal Continual Learner: An Agent That Never Forgets

https://github.com/xialeiliu/GFR-IL

공식 코드

Generative Feature Replay For Class-Incremental Learning

https://github.com/xialeiliu/long-tailed-cil

공식 코드

Long-Tailed Class Incremental Learning

https://github.com/xianglinyang/sentrycam

공식 코드

Exploring the Evolution of Hidden Activations with Live-Update Visualization

https://github.com/xiaojieli0903/ckpd-fscil

공식 코드

Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning

https://github.com/xiaojieli0903/cpkd_fscil

공식 코드

Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning

https://github.com/xiaojieli0903/mamba-fscil

공식 코드

Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning

https://github.com/xiaojihh/cl_all-in-one

공식 코드

Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure

https://github.com/xinchen930/ssf-strategic-selection-and-forgetting

공식 코드

Continual Learning with Strategic Selection and Forgetting for Network Intrusion Detection

https://github.com/xli04/cvqa

공식 코드

MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering

https://github.com/xmengxin/mfgr

공식 코드

Memory-Free Generative Replay For Class-Incremental Learning

https://github.com/xmindflow/braincl

공식 코드

Modality-Independent Brain Lesion Segmentation with Privacy-aware Continual Learning

https://github.com/xu-ji/ARM

공식 코드

Automatic Recall Machines: Internal Replay, Continual Learning and the Brain

https://github.com/xumengyaamy/synthetic_cat_sd

공식 코드

Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery

https://github.com/xup5/MEGA

공식 코드

Memorization and Knowledge Injection in Gated LLMs

https://github.com/yangjl1215/cosam

공식 코드

Continual Learning for Segment Anything Model Adaptation

https://github.com/yaoyao-liu/class-incremental-learning

공식 코드

Adaptive Aggregation Networks for Class-Incremental Learning

https://github.com/yaoyao-liu/mnemonics

공식 코드

Mnemonics Training: Multi-Class Incremental Learning without Forgetting

https://github.com/yaoyao-liu/online-hyperparameter-optimization

공식 코드

Online Hyperparameter Optimization for Class-Incremental Learning

https://github.com/yaqianzhang/repeatedaugmentedrehearsal

공식 코드

A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

https://github.com/yasesf93/CrossGradientAggregation

공식 코드

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data

https://github.com/yasir-ghunaim/realtimeocl

공식 코드

Real-Time Evaluation in Online Continual Learning: A New Hope

https://github.com/yawencui/cmoa

공식 코드

Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters

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