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/linzhiqiu/continual-learning

공식 코드

The CLEAR Benchmark: Continual LEArning on Real-World Imagery

https://github.com/linzwcs/see

공식 코드

SEE: Continual Fine-tuning with Sequential Ensemble of Experts

https://github.com/liuh127/FSCIL-via-Entropy-regularized-DF-Replay

공식 코드

Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay

https://github.com/liuruiqi0520/E2Net

공식 코드

E2Net: Resource-Efficient Continual Learning with Elastic Expansion Network

https://github.com/liutianlin0121/contSentEmbed

공식 코드

Continual Learning for Sentence Representations Using Conceptors

https://github.com/liuyejia/gps_cl

공식 코드

Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning

https://github.com/liuyuchen-cz/f-oal

공식 코드

F-OAL: Forward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning

https://github.com/lkorycki/rsb

공식 코드

Class-Incremental Experience Replay for Continual Learning under Concept Drift

https://github.com/lkyddd/gradma

공식 코드

GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting

https://github.com/lloongx/diki

공식 코드

Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

https://github.com/longbai1006/cs-vqla

공식 코드

Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery

https://github.com/loribonna/cssl

공식 코드

Continual Semi-Supervised Learning through Contrastive Interpolation Consistency

https://github.com/lrzpellegrini/CL-CORe-App

공식 코드

Continual Learning at the Edge: Real-Time Training on Smartphone Devices

https://github.com/lsabetta/mind

공식 코드

MIND: Multi-Task Incremental Network Distillation

https://github.com/lttm/cl-pcss

공식 코드

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data

https://github.com/lttm/fedspace

공식 코드

Asynchronous Federated Continual Learning

https://github.com/lttm/recall

공식 코드

RECALL: Replay-based Continual Learning in Semantic Segmentation

https://github.com/luckeciano/TD-VCL

공식 코드

Temporal-Difference Variational Continual Learning

https://github.com/lucydyu/awesome-multimodal-continual-learning

공식 코드

Recent Advances of Multimodal Continual Learning: A Comprehensive Survey

https://github.com/luk-st/continual-lora

공식 코드

Low-Rank Continual Personalization of Diffusion Models

https://github.com/luoyan407/congruency

공식 코드

Direction Concentration Learning: Enhancing Congruency in Machine Learning

https://github.com/luoyan407/grad_prediction

공식 코드

Learning to Predict Gradients for Semi-Supervised Continual Learning

https://github.com/lvyilin/adab2n

공식 코드

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

https://github.com/lykaust15/SupportNet

공식 코드

SupportNet: solving catastrophic forgetting in class incremental learning with support data

https://github.com/lywang3081/AFEC

공식 코드

AFEC: Active Forgetting of Negative Transfer in Continual Learning

https://github.com/lywang3081/Awesome-Continual-Learning

공식 코드

A Comprehensive Survey of Continual Learning: Theory, Method and Application

https://github.com/lywang3081/MRDC

공식 코드

Memory Replay with Data Compression for Continual Learning

https://github.com/lywang3081/TMNs

공식 코드

Triple Memory Networks: a Brain-Inspired Method for Continual Learning

https://github.com/lywang3081/caf

공식 코드

Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence

https://github.com/lywang3081/coscl

공식 코드

CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One

https://github.com/lzvv123456/contrastive-prototypical-prompt

공식 코드

Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning

https://github.com/lzvv123456/steering-prototypes-with-prompt-tuning-for-rehearsal-free-continual-learning

공식 코드

Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning

https://github.com/m-3lab/im-iad

공식 코드

IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing

https://github.com/m-3lab/open-iad

공식 코드

IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing

https://github.com/m-j-tilley/LXDG

공식 코드

Artificial Neuronal Ensembles with Learned Context Dependent Gating

https://github.com/ma3oun/hrn

공식 코드

Continual learning using hash-routed convolutional neural networks

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