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/chen-xw/drc-cil

공식 코드

Dynamic Residual Classifier for Class Incremental Learning

https://github.com/chen-yizhu/gacl

공식 코드

GACL: Exemplar-Free Generalized Analytic Continual Learning

https://github.com/chenxing6666/dap

공식 코드

Dynamically Anchored Prompting for Task-Imbalanced Continual Learning

https://github.com/chenzeno/FOO-VB

공식 코드

Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates

https://github.com/chenzk202212/lwi

공식 코드

Learning without Isolation: Pathway Protection for Continual Learning

https://github.com/chrhenning/hypercl

공식 코드

Continual learning with hypernetworks

https://github.com/chrhenning/posterior_replay_cl

공식 코드

Posterior Meta-Replay for Continual Learning

https://github.com/chrismcclurg/fscil-acs

공식 코드

Active Class Selection for Few-Shot Class-Incremental Learning

https://github.com/christina200/online-lora-official

공식 코드

Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation

https://github.com/cisco-open/DeepVision/tree/main/recallm

공식 코드

RecallM: An Adaptable Memory Mechanism with Temporal Understanding for Large Language Models

https://github.com/cl-premonition/premonition

공식 코드

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning

https://github.com/clear-nus/selective-amnesia

공식 코드

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

https://github.com/cliveyn/scstory

공식 코드

SCStory: Self-supervised and Continual Online Story Discovery

https://github.com/cloudcjf/ccl

공식 코드

CCL: Continual Contrastive Learning for LiDAR Place Recognition

https://github.com/clovaai/ECLIPSE

공식 코드

ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

https://github.com/clovaai/SSUL

공식 코드

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

https://github.com/clovaai/puridiver

공식 코드

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries

https://github.com/clovaai/rainbow-memory

공식 코드

Rainbow Memory: Continual Learning with a Memory of Diverse Samples

https://github.com/cly234/lreid-krkc

공식 코드

Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation

https://github.com/cmnfriend/o-lora

공식 코드

Orthogonal Subspace Learning for Language Model Continual Learning

https://github.com/cogsys-tudelft/chameleon

공식 코드

Chameleon: A MatMul-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data

https://github.com/conditionwang/fcil

공식 코드

Federated Class-Incremental Learning

https://github.com/continualai/avalanche-rl

공식 코드

Avalanche RL: a Continual Reinforcement Learning Library

https://github.com/continualai/clvision-challenge-2022

공식 코드

3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding

https://github.com/cranial-xix/continual-learning-private-unlearning

공식 코드

Continual Learning and Private Unlearning

https://github.com/crouzbehmeshkin/lasp

공식 코드

Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks

https://github.com/cruiseresearchgroup/vilco

공식 코드

ViLCo-Bench: VIdeo Language COntinual learning Benchmark

https://github.com/csiro-robotics/sdcl

공식 코드

Subspace Distillation for Continual Learning

https://github.com/csm9493/CPR_CL

공식 코드

CPR: Classifier-Projection Regularization for Continual Learning

https://github.com/csm9493/PNR

공식 코드

Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning

https://github.com/csm9493/TaskBalancedBN

공식 코드

Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning

https://github.com/csm9493/UCL

공식 코드

Uncertainty-based Continual Learning with Adaptive Regularization

https://github.com/cyjie429/rego

공식 코드

Region-Based Optimization in Continual Learning for Audio Deepfake Detection

https://github.com/cywinski/guide

공식 코드

GUIDE: Guidance-based Incremental Learning with Diffusion Models

https://github.com/cywinski/multiband_gan

공식 코드

Adapt & Align: Continual Learning with Generative Models Latent Space Alignment

https://github.com/czbnlp/LPE-SQL

공식 코드

Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQL

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