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/aioz-ai/sac

공식 코드

Fine-Grained Visual Classification using Self Assessment Classifier

https://github.com/akarshkumar0101/fer

공식 코드

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis

https://github.com/albinsou/ocl_survey

공식 코드

A Comprehensive Empirical Evaluation on Online Continual Learning

https://github.com/albinsou/online_ema

공식 코드

Improving Online Continual Learning Performance and Stability with Temporal Ensembles

https://github.com/alejandromllo/action_flow_matching

공식 코드

Action Flow Matching for Continual Robot Learning

https://github.com/alessiabertugli/FUSION

공식 코드

Few-Shot Unsupervised Continual Learning through Meta-Examples

https://github.com/alexk1704/scclv2

공식 코드

Adiabatic replay for continual learning

https://github.com/alexlioralexli/noncontrastive-ssl

공식 코드

Understanding Collapse in Non-Contrastive Siamese Representation Learning

https://github.com/aliayub7/CBCL

공식 코드

Cognitively-Inspired Model for Incremental Learning Using a Few Examples

https://github.com/aliayub7/EEC

공식 코드

EEC: Learning to Encode and Regenerate Images for Continual Learning

https://github.com/aliayub7/cbcl-pr

공식 코드

CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics

https://github.com/aliayub7/cl_hri

공식 코드

Continual Learning through Human-Robot Interaction: Human Perceptions of a Continual Learning Robot in Repeated Interactions

https://github.com/alteia-ai/icss

공식 코드

Weakly-supervised continual learning for class-incremental segmentation

https://github.com/alviur/cvpr_pfr

공식 코드

Continually Learning Self-Supervised Representations with Projected Functional Regularization

https://github.com/alviur/ldc

공식 코드

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

https://github.com/alviur/pocon_wacv2024

공식 코드

Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning

https://github.com/amazon-research/replay-based-recurrent-rl

공식 코드

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

https://github.com/amazon-research/sp-cil

공식 코드

Class-Incremental Learning with Strong Pre-trained Models

https://github.com/amazon-science/replay-based-recurrent-rl

공식 코드

Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges

https://github.com/amgao/rls-onlinetrack

공식 코드

Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking

https://github.com/aminbana/MTL-Theory

공식 코드

Theoretical Insights into Overparameterized Models in Multi-Task and Replay-Based Continual Learning

https://github.com/amir4g/clvos23

공식 코드

CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning

https://github.com/anapplecore/mose

공식 코드

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation

https://github.com/andreacossu/continual-pretraining-nlp-vision

공식 코드

Continual Pre-Training Mitigates Forgetting in Language and Vision

https://github.com/andreacossu/explainable-continual-learning

공식 코드

A Protocol for Continual Explanation of SHAP

https://github.com/andreamad8/ToDCL

공식 코드

Continual Learning in Task-Oriented Dialogue Systems

https://github.com/andrew-r96/DistilledReplay

공식 코드

Distilled Replay: Overcoming Forgetting through Synthetic Samples

https://github.com/angusmaiden/complex-fer

공식 코드

Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features

https://github.com/annaVettoruzzo/L2L_with_attention

공식 코드

Learning to Learn without Forgetting using Attention

https://github.com/anticdimi/CloSe

공식 코드

CloSe: A 3D Clothing Segmentation Dataset and Model

https://github.com/antoniocarta/data-agnostic-consolidation

공식 코드

Projected Latent Distillation for Data-Agnostic Consolidation in Distributed Continual Learning

https://github.com/antoniocarta/ex_model_cl

공식 코드

Ex-Model: Continual Learning from a Stream of Trained Models

https://github.com/anwarmaxsum/agla

공식 코드

Assessor-Guided Learning for Continual Environments

https://github.com/anwarmaxsum/flower

공식 코드

Few-Shot Continual Learning via Flat-to-Wide Approaches

https://github.com/anwarmaxsum/pip

공식 코드

PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning

https://github.com/anwarmaxsum/unisa

공식 코드

Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification

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