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/VDIGPKU/ContinualContrastiveLearning

공식 코드

Continual Contrastive Learning for Image Classification

https://github.com/VICO-UoE/DatasetCondensation

공식 코드

Dataset Condensation with Gradient Matching

https://github.com/VerwimpEli/CLAD

공식 코드

CLAD: A realistic Continual Learning benchmark for Autonomous Driving

https://github.com/WoodScene/RoS

공식 코드

Continual Dialogue State Tracking via Reason-of-Select Distillation

https://github.com/WoodScene/TaSL

공식 코드

KIF: Knowledge Identification and Fusion for Language Model Continual Learning

https://github.com/Xnhyacinth/DATA

공식 코드

DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning

https://github.com/Xu-Linfeng/UESTC_MMEA_CL_main

공식 코드

Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning

https://github.com/YBIO/CPP

공식 코드

Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images

https://github.com/YanFangCS/IPSeg

공식 코드

IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation

https://github.com/Yujun-Shi/BLIP

공식 코드

Continual Learning via Bit-Level Information Preserving

https://github.com/YukunLi99/CoLeCLIP

공식 코드

CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning

https://github.com/Yunbo-max/HyDRO

공식 코드

Random Walk Guided Hyperbolic Graph Distillation

https://github.com/ZHUANGHP/Analytic-continual-learning

공식 코드

ACIL: Analytic Class-Incremental Learning with Absolute Memorization and Privacy Protection

https://github.com/Zhanxin-Gao/CPrompt

공식 코드

Consistent Prompting for Rehearsal-Free Continual Learning

https://github.com/Zhong-Zhengyi/SacFL-Code

공식 코드

SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices

https://github.com/ZixuanKe/CAT

공식 코드

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks

https://github.com/aI-area/CEL

공식 코드

CEL: A Continual Learning Model for Disease Outbreak Prediction by Leveraging Domain Adaptation via Elastic Weight Consolidation

https://github.com/aakutalev/ewc-features

공식 코드

Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruning

https://github.com/aaltoml/sequential-gp

공식 코드

Memory-Based Dual Gaussian Processes for Sequential Learning

https://github.com/aaltovision/cl_hscnet

공식 코드

Continual Learning for Image-Based Camera Localization

https://github.com/abdohelmy/D-3Former

공식 코드

D3Former: Debiased Dual Distilled Transformer for Incremental Learning

https://github.com/abhishekpanigrahi1996/Skill-Localization-by-grafting

공식 코드

Task-Specific Skill Localization in Fine-tuned Language Models

https://github.com/adaruna3/continual-kge

공식 코드

Continual Learning of Knowledge Graph Embeddings

https://github.com/adekhovich/continual_defect_segmentation

공식 코드

Continual learning for surface defect segmentation by subnetwork creation and selection

https://github.com/adekhovich/continual_prune_and_select

공식 코드

Continual Prune-and-Select: Class-incremental learning with specialized subnetworks

https://github.com/adinlab/CDDP-Continual-Learning-of-Multi-modal-Dynamics-with-External-Memory

공식 코드

Continual Learning of Multi-modal Dynamics with External Memory

https://github.com/adityashahane10/gotham--graph-based-class-incremental-learning-framework-under-weak-supervision

공식 코드

GOTHAM: Graph Class Incremental Learning Framework under Weak Supervision

https://github.com/ahmadisahar/accv_fcil3d

공식 코드

Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor

https://github.com/ahmedhajyahmed/drdrl

공식 코드

An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems

https://github.com/ahnobari/ActivationInformedMerging

공식 코드

Activation-Informed Merging of Large Language Models

https://github.com/aignlai/gddsg

공식 코드

Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping

https://github.com/aignlai/holitrans

공식 코드

Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer

https://github.com/aimagelab/casper

공식 코드

Latent Spectral Regularization for Continual Learning

https://github.com/aimagelab/lider

공식 코드

On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning

https://github.com/aimagelab/mammoth

공식 코드

Dark Experience for General Continual Learning: a Strong, Simple Baseline

https://github.com/aimagelab/scad-lod-2024

공식 코드

An Attention-based Representation Distillation Baseline for Multi-Label Continual Learning

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