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/hanxixiao/rcl

공식 코드

Improving Data-aware and Parameter-aware Robustness for Continual Learning

https://github.com/haoranchen/promptfusion

공식 코드

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

https://github.com/hastings24/rethinking_er

공식 코드

Rethinking Experience Replay: a Bag of Tricks for Continual Learning

https://github.com/hawkrobe/continual-adaptation

공식 코드

Continual adaptation for efficient machine communication

https://github.com/hawkrobe/conventions_model

공식 코드

From partners to populations: A hierarchical Bayesian account of coordination and convention

https://github.com/heidelberg-nlp/c2gen

공식 코드

Exploring Continual Learning of Compositional Generalization in NLI

https://github.com/hhihn/HVCL

공식 코드

Mixture-of-Variational-Experts for Continual Learning

https://github.com/hhliu79/TWP

공식 코드

Overcoming Catastrophic Forgetting in Graph Neural Networks

https://github.com/hikmatkhan/adrm

공식 코드

Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning

https://github.com/hiroid/oodf

공식 코드

Out-of-distribution forgetting: vulnerability of continual learning to intra-class distribution shift

https://github.com/hit-leaderone/filp-3d

공식 코드

FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models

https://github.com/hit-leaderone/flip-3d

공식 코드

FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models

https://github.com/hku-medai/conslide

공식 코드

ConSlide: Asynchronous Hierarchical Interaction Transformer with Breakup-Reorganize Rehearsal for Continual Whole Slide Image Analysis

https://github.com/hoangthangta/stsm

공식 코드

Self-training from Self-memory in Data-to-text Generation

https://github.com/hongsinlee/flair

공식 코드

Enhancing Robustness in Incremental Learning with Adversarial Training

https://github.com/hossein-rezaei624/acr

공식 코드

Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay

https://github.com/hossein-rezaei624/casp

공식 코드

Class-Adaptive Sampling Policy for Efficient Continual Learning

https://github.com/houyon/online-distillation-cl

공식 코드

Online Distillation with Continual Learning for Cyclic Domain Shifts

https://github.com/hpdeventer/kasam

공식 코드

KASAM: Spline Additive Models for Function Approximation

https://github.com/hrlblab/IRS

공식 코드

IRS: Incremental Relationship-guided Segmentation for Digital Pathology

https://github.com/hsilva664/discrete_nn

공식 코드

What to Do When Your Discrete Optimization Is the Size of a Neural Network?

https://github.com/huang50213/AIM-Fewshot-Continual

공식 코드

Few-Shot and Continual Learning with Attentive Independent Mechanisms

https://github.com/huangyz0918/kws-continual-learning

공식 코드

Progressive Continual Learning for Spoken Keyword Spotting

https://github.com/huaxiuyao/HSML

공식 코드

Hierarchically Structured Meta-learning

https://github.com/huaxiuyao/wild-time

공식 코드

Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time

https://github.com/huiyiwang01/sema-cl

공식 코드

Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning

https://github.com/hummosa/thalamus

공식 코드

Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

https://github.com/hunarbatra/elastic-variational-continual-learning

공식 코드

EVCL: Elastic Variational Continual Learning with Weight Consolidation

https://github.com/hy2mk/cgcd

공식 코드

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

https://github.com/hyintell/citb

공식 코드

CITB: A Benchmark for Continual Instruction Tuning

https://github.com/hyqlat/tcl

공식 코드

Temporal Continual Learning with Prior Compensation for Human Motion Prediction

https://github.com/iSEE-Laboratory/Continual-AQA

공식 코드

Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling

https://github.com/iacobo/continual

공식 코드

Continual learning of longitudinal health records

https://github.com/iamwangyabin/esn

공식 코드

Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference

https://github.com/iamwangyabin/s-prompts

공식 코드

S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning

https://github.com/ibcl-anon/ibcl

공식 코드

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

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