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/DeepakSridhar/fgdm

공식 코드

Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis

https://github.com/DigiTurk84/class-incremental-polytope

공식 코드

Class-incremental Learning with Pre-allocated Fixed Classifiers

https://github.com/DonkeyShot21/batch-level-distillation

공식 코드

Online Continual Learning under Extreme Memory Constraints

https://github.com/DoubleMuL/ADER

공식 코드

ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation

https://github.com/EMLS-ICTCAS/CLFD

공식 코드

Continual Learning in the Frequency Domain

https://github.com/EVOKE-LMM/EVOKE

공식 코드

When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways

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

공식 코드

ScaIL: Classifier Weights Scaling for Class Incremental Learning

https://github.com/EkdeepSLubana/EMR

공식 코드

How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation

https://github.com/EkdeepSLubana/QRforgetting

공식 코드

How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation

https://github.com/ElementAI/osaka

공식 코드

Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning

https://github.com/ElifCerenGokYildirim/DataDietCL

공식 코드

Continual Learning on a Data Diet

https://github.com/Eric8932/Create-and-Find-Flatness

공식 코드

Create and Find Flatness: Building Flat Training Spaces in Advance for Continual Learning

https://github.com/FelixWiewel/CCMCL

공식 코드

Condensed Composite Memory Continual Learning

https://github.com/G-U-N/ECCV22-FOSTER

공식 코드

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

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

공식 코드

Class-Incremental Learning with Generative Classifiers

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

공식 코드

Generative replay with feedback connections as a general strategy for continual learning

https://github.com/GRASP-ML/Mendez2020Compositional

공식 코드

Lifelong Learning of Compositional Structures

https://github.com/GT-RIPL/AlwaysBeDreaming-DFCIL

공식 코드

Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning

https://github.com/GT-RIPL/Continual-Learning-Benchmark

공식 코드

Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines

https://github.com/GT-RIPL/DistillMatch-SSCL

공식 코드

Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer

https://github.com/GT-SALT/Adaptive-Compositional-Modules

공식 코드

Continual Sequence Generation with Adaptive Compositional Modules

https://github.com/GT-SALT/IDBR

공식 코드

Continual Learning for Text Classification with Information Disentanglement Based Regularization

https://github.com/GhadaSokar/AFAF

공식 코드

Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks

https://github.com/GhadaSokar/Invariant-Representation-for-Continual-Learning

공식 코드

Learning Invariant Representation for Continual Learning

https://github.com/GhadaSokar/Self-Attention-Meta-Learner-for-Continual-Learning

공식 코드

Self-Attention Meta-Learner for Continual Learning

https://github.com/GhadaSokar/SpaceNet

공식 코드

SpaceNet: Make Free Space For Continual Learning

https://github.com/GitiHubi/deepContinualAuditing

공식 코드

Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data

https://github.com/GoodAI/goodai-ltm-benchmark

공식 코드

Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models

https://github.com/Guang000/Awesome-Dataset-Distillation

공식 코드

A Survey on Dataset Distillation: Approaches, Applications and Future Directions

https://github.com/GuangmingZhu/SketchIME

공식 코드

Sketch Input Method Editor: A Comprehensive Dataset and Methodology for Systematic Input Recognition

https://github.com/HAIV-Lab/Knowe

공식 코드

Coarse-To-Fine Incremental Few-Shot Learning

https://github.com/Haoran-S/ICASSP2021

공식 코드

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

https://github.com/Haoran-S/TSP_CL

공식 코드

Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective

https://github.com/HobbitLong/SupContrast

공식 코드

Supervised Contrastive Learning

https://github.com/INK-USC/CLIF

공식 코드

Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning

https://github.com/INK-USC/GMED

공식 코드

Gradient-based Editing of Memory Examples for Online Task-free Continual Learning

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