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/yawencui/uad-ce

공식 코드

Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning

https://github.com/ybio/surveycss

공식 코드

A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application

https://github.com/yc14600/discriminative-representation-loss

공식 코드

Semi-Discriminative Representation Loss for Online Continual Learning

https://github.com/ycheoo/fppl

공식 코드

FPPL: An Efficient and Non-IID Robust Federated Continual Learning Framework

https://github.com/ycheoo/pmae

공식 코드

Masked Autoencoders are Parameter-Efficient Federated Continual Learners

https://github.com/yeerwen/medcoss

공식 코드

Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning

https://github.com/yellowpancake/tcil

공식 코드

Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

https://github.com/yezilaixi/kt-rcnet

공식 코드

Knowledge Transfer-Driven Few-Shot Class-Incremental Learning

https://github.com/yhchen12101/FGP-ICL

공식 코드

Class-incremental Learning with Rectified Feature-Graph Preservation

https://github.com/yifan-song793/infocl

공식 코드

InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective

https://github.com/yixinghuang/itlsurvey

공식 코드

A Survey of Incremental Transfer Learning: Combining Peer-to-Peer Federated Learning and Domain Incremental Learning for Multicenter Collaboration

https://github.com/yklochkov-bytedance/mt-unlearn

공식 코드

A mean teacher algorithm for unlearning of language models

https://github.com/yong-dai/pc

공식 코드

Prompt Customization for Continual Learning

https://github.com/yongchao97/FRePo

공식 코드

Dataset Distillation using Neural Feature Regression

https://github.com/yongzhang-tan/adbs

공식 코드

Adaptive Decision Boundary for Few-Shot Class-Incremental Learning

https://github.com/yonseivnl/earl

공식 코드

Learning Equi-angular Representations for Online Continual Learning

https://github.com/yousuf907/SIESTA

공식 코드

SIESTA: Efficient Online Continual Learning with Sleep

https://github.com/yu-rp/kanbefair

공식 코드

KAN or MLP: A Fairer Comparison

https://github.com/yuelinan/fedjudge

공식 코드

FedJudge: Federated Legal Large Language Model

https://github.com/yujieli42/pro-kt

공식 코드

Learning to Prompt Knowledge Transfer for Open-World Continual Learning

https://github.com/yujun-shi/cwd

공식 코드

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

https://github.com/yuliangcai2022/clumo

공식 코드

CluMo: Cluster-based Modality Fusion Prompt for Continual Learning in Visual Question Answering

https://github.com/yulonghui/moca

공식 코드

Continual Learning by Modeling Intra-Class Variation

https://github.com/yulu0724/SDC-IL

공식 코드

Semantic Drift Compensation for Class-Incremental Learning

https://github.com/yunfei-teng/dco

공식 코드

Overcoming Catastrophic Forgetting via Direction-Constrained Optimization

https://github.com/yunhuiguo/Depthwise_Convolution_for_Multiple_Domain_Learning

공식 코드

Depthwise Convolution is All You Need for Learning Multiple Visual Domains

https://github.com/yuyangdu01/llm-cl-vqa

공식 코드

LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery

https://github.com/zackschen/CGP

공식 코드

Class Gradient Projection For Continual Learning

https://github.com/zackschen/IBM-Net

공식 코드

Towards Redundancy-Free Sub-networks in Continual Learning

https://github.com/zackschen/cucl

공식 코드

CUCL: Codebook for Unsupervised Continual Learning

https://github.com/zalanborsos/bilevel_coresets

공식 코드

Coresets via Bilevel Optimization for Continual Learning and Streaming

https://github.com/zaocan666/af-fcl

공식 코드

Accurate Forgetting for Heterogeneous Federated Continual Learning

https://github.com/zbwxp/SegVit

공식 코드

SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers

https://github.com/zhang-jinghua/dbc-fscil

공식 코드

A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition

https://github.com/zhangchbin/rcil

공식 코드

Representation Compensation Networks for Continual Semantic Segmentation

https://github.com/zhanglab-deepneurocoglab/csegg

공식 코드

Adaptive Visual Scene Understanding: Incremental Scene Graph Generation

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