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/vihan-lakshman/diminishing-returns-wide-continual-learning

공식 코드

On the Diminishing Returns of Width for Continual Learning

https://github.com/vimar-gu/ssd

공식 코드

Summarizing Stream Data for Memory-Constrained Online Continual Learning

https://github.com/vinuni-vishc/cg-imif

공식 코드

Multi-stream Fusion for Class Incremental Learning in Pill Image Classification

https://github.com/visiontao/cl

공식 코드

Continual Learning with Strong Experience Replay

https://github.com/visiontao/pfcl

공식 코드

Prior-Free Continual Learning with Unlabeled Data in the Wild

https://github.com/vita-qzh/apart

공식 코드

Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning

https://github.com/vkverma01/EFT

공식 코드

Efficient Feature Transformations for Discriminative and Generative Continual Learning

https://github.com/vt-nlp/ice

공식 코드

Teamwork Is Not Always Good: An Empirical Study of Classifier Drift in Class-incremental Information Extraction

https://github.com/wabbajack1/tapd

공식 코드

Continual Deep Reinforcement Learning with Task-Agnostic Policy Distillation

https://github.com/wadeyin9712/dynosaur

공식 코드

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation

https://github.com/wang-chen/LGL

공식 코드

Lifelong Graph Learning

https://github.com/wang-chen/lgl-action-recognition

공식 코드

Lifelong Graph Learning

https://github.com/wang-ml-lab/llm-continual-learning-survey

공식 코드

Continual Learning of Large Language Models: A Comprehensive Survey

https://github.com/wangbing1416/daedcmd

공식 코드

Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors

https://github.com/wangkai930418/ERD

공식 코드

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition

https://github.com/wangkai930418/hcv_iirc

공식 코드

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

https://github.com/wangkiw/iclr23-memo

공식 코드

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

https://github.com/wangkiw/teen

공식 코드

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

https://github.com/wannaa/c-flat

공식 코드

Make Continual Learning Stronger via C-Flat

https://github.com/wcxwcxw/gorp

공식 코드

Continual Gradient Low-Rank Projection Fine-Tuning for LLMs

https://github.com/weiguopian/av-cil_iccv2023

공식 코드

Audio-Visual Class-Incremental Learning

https://github.com/weiguopian/contav-sep_neurips2024

공식 코드

Continual Audio-Visual Sound Separation

https://github.com/weijiawu/cisdq

공식 코드

Continual Learning for Image Segmentation with Dynamic Query

https://github.com/weilllllls/onpro

공식 코드

Online Prototype Learning for Online Continual Learning

https://github.com/wendongzh/continual_visual_control

공식 코드

Predictive Experience Replay for Continual Visual Control and Forecasting

https://github.com/wengweng001/CLAMP_torch

공식 코드

Cross-Domain Continual Learning via CLAMP

https://github.com/wengzejia1/open-vclip

공식 코드

Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization

https://github.com/wentianzhang-ml/dmd

공식 코드

Dynamically Masked Discriminator for Generative Adversarial Networks

https://github.com/wenyudu/migu

공식 코드

Unlocking Continual Learning Abilities in Language Models

https://github.com/which47/llmcl

공식 코드

Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning

https://github.com/whitesnowdrop/mufan

공식 코드

New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

https://github.com/will-doherty/clofai

공식 코드

CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning

https://github.com/williamyue37/t-dgr

공식 코드

t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making

https://github.com/wisdeth14/molerecruitment

공식 코드

Mole Recruitment: Poisoning of Image Classifiers via Selective Batch Sampling

https://github.com/wish44165/ntd

공식 코드

Data Stream Sampling with Fuzzy Task Boundaries and Noisy Labels

https://github.com/witdsl/krt-mlcil

공식 코드

Knowledge Restore and Transfer for Multi-label Class-Incremental Learning

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