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/simplify23/MRN

공식 코드

MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition

https://github.com/skeskinen/pairwise_online_learning

공식 코드

Task agnostic continual learning with Pairwise layer architecture

https://github.com/skezle/bayes_cl_posterior

공식 코드

On Sequential Bayesian Inference for Continual Learning

https://github.com/skezle/continual-dreamer

공식 코드

The Effectiveness of World Models for Continual Reinforcement Learning

https://github.com/skezle/owl

공식 코드

Same State, Different Task: Continual Reinforcement Learning without Interference

https://github.com/skrighyz/osiris

공식 코드

Integrating Present and Past in Unsupervised Continual Learning

https://github.com/skylorh/FedCLASS

공식 코드

Federated Class-Incremental Learning with New-Class Augmented Self-Distillation

https://github.com/skyofbeginning/fedmgp

공식 코드

Personalized Federated Continual Learning via Multi-granularity Prompt

https://github.com/sled-group/comparative-learning

공식 코드

Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition

https://github.com/snu-list/most

공식 코드

MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learning

https://github.com/snumprlab/cl-alfred

공식 코드

Online Continual Learning For Interactive Instruction Following Agents

https://github.com/sonycslparis/deep_srda

공식 코드

Continual Learning with Deep Streaming Regularized Discriminant Analysis

https://github.com/sonyresearch/coala

공식 코드

COALA: A Practical and Vision-Centric Federated Learning Platform

https://github.com/soochan-lee/CN-DPM

공식 코드

A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning

https://github.com/soochan-lee/cl-as-seq

공식 코드

Recasting Continual Learning as Sequence Modeling

https://github.com/soochan-lee/sb-mcl

공식 코드

Learning to Continually Learn with the Bayesian Principle

https://github.com/soolab/simcis

공식 코드

Rethinking Query-based Transformer for Continual Image Segmentation

https://github.com/speechbrain/benchmarks

공식 코드

CL-MASR: A Continual Learning Benchmark for Multilingual ASR

https://github.com/sperimental3/charon

공식 코드

Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning

https://github.com/srebuffi/iCaRL

공식 코드

iCaRL: Incremental Classifier and Representation Learning

https://github.com/srebuffi/residual_adapters

공식 코드

Learning multiple visual domains with residual adapters

https://github.com/srvCodes/continual-learning-benchmark

공식 코드

Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis

https://github.com/srvCodes/continual_learning_with_vit

공식 코드

Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization

https://github.com/srvcodes/clap4clip

공식 코드

CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models

https://github.com/sssunqing/example_influence_cl

공식 코드

Exploring Example Influence in Continual Learning

https://github.com/stapaw/stp

공식 코드

Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning

https://github.com/steffengra/dl_lottery

공식 코드

Robust Deep Reinforcement Learning Scheduling via Weight Anchoring

https://github.com/sterzhang/core

공식 코드

CORE: Mitigating Catastrophic Forgetting in Continual Learning through Cognitive Replay

https://github.com/stevenvdeeckt/cgn_cl_dialect

공식 코드

Continual Learning for Monolingual End-to-End Automatic Speech Recognition

https://github.com/stevenvdeeckt/online-cl-for-asr

공식 코드

Rehearsal-Free Online Continual Learning for Automatic Speech Recognition

https://github.com/stevenvdeeckt/unsupervised-ocl-for-asr

공식 코드

Unsupervised Online Continual Learning for Automatic Speech Recognition

https://github.com/stonemo/cign

공식 코드

Class-Incremental Grouping Network for Continual Audio-Visual Learning

https://github.com/sud0301/essentials_for_CIL

공식 코드

Essentials for Class Incremental Learning

https://github.com/summerfieldlab/flesch_nagy_etal_hebbcl

공식 코드

Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals

https://github.com/sun-hailong/aaai25-mos

공식 코드

MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

https://github.com/sun-hailong/cvpr24-ease

공식 코드

Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning

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