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/joonh-kim/etm

공식 코드

Continual Unsupervised Domain Adaptation for Semantic Segmentation

https://github.com/josephkj/eli

공식 코드

Energy-based Latent Aligner for Incremental Learning

https://github.com/junghunoh/closer_eccv2024

공식 코드

CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning

https://github.com/juzhengz/lori

공식 코드

LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation

https://github.com/jwparktom/continual-bert

공식 코드

Continual BERT: Continual Learning for Adaptive Extractive Summarization of COVID-19 Literature

https://github.com/k-gyuhak/clom

공식 코드

Continual Learning Based on OOD Detection and Task Masking

https://github.com/k-gyuhak/clood

공식 코드

Learnability and Algorithm for Continual Learning

https://github.com/k-gyuhak/more

공식 코드

A Multi-Head Model for Continual Learning via Out-of-Distribution Replay

https://github.com/k-gyuhak/wptp

공식 코드

A Theoretical Study on Solving Continual Learning

https://github.com/k1nght/online_cl_logit_adjusted_softmax

공식 코드

Online Continual Learning via Logit Adjusted Softmax

https://github.com/kaist-dmlab/adapromptcl

공식 코드

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

https://github.com/kangzhiq/misa

공식 코드

Advancing Prompt-Based Methods for Replay-Independent General Continual Learning

https://github.com/kangzhiq/nncsl

공식 코드

A soft nearest-neighbor framework for continual semi-supervised learning

https://github.com/kclip/bayesian-snn

공식 코드

Bayesian Continual Learning via Spiking Neural Networks

https://github.com/kelvin-ywc/lpi

공식 코드

Low-rank Prompt Interaction for Continual Vision-Language Retrieval

https://github.com/kerrydrx/escort

공식 코드

Prompt-Based Exemplar Super-Compression and Regeneration for Class-Incremental Learning

https://github.com/kevinlight831/ctp

공식 코드

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

https://github.com/khu-agi/ocgcd

공식 코드

Online Continuous Generalized Category Discovery

https://github.com/khu-agi/privilege

공식 코드

Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners

https://github.com/khurramjaved96/online-causal-models

공식 코드

Learning Causal Models Online

https://github.com/kibok90/iccv2019-inc

공식 코드

Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild

https://github.com/kietzmannlab/keep-moving

공식 코드

Keep Moving: identifying task-relevant subspaces to maximise plasticity for newly learned tasks

https://github.com/kikihub/consense

공식 코드

ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking

https://github.com/kim-sanghwan/ancl

공식 코드

Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning

https://github.com/kimyuji/evolvingqa_benchmark

공식 코드

Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models

https://github.com/kitbransby/class-incremental-learning-echo

공식 코드

Multi-Site Class-Incremental Learning with Weighted Experts in Echocardiography

https://github.com/kiyan-rezaee/systematic-literature-review-on-online-continual-learning

공식 코드

Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks

https://github.com/kkhetarpal/unrealwithattention

공식 코드

Attend Before you Act: Leveraging human visual attention for continual learning

https://github.com/klauscc/dam

공식 코드

DAM: Dynamic Adapter Merging for Continual Video QA Learning

https://github.com/klightz/Firefly

공식 코드

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks

https://github.com/kminsoo/afc

공식 코드

Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation

https://github.com/kmsamuel/cl-for-engineering-release

공식 코드

Continual Learning Strategies for 3D Engineering Regression Problems: A Benchmarking Study

https://github.com/knowledgetechnologyuhh/drill

공식 코드

DRILL: Dynamic Representations for Imbalanced Lifelong Learning

https://github.com/kreimanlab/VariationalPrototypeReplaysCL

공식 코드

Variational Prototype Replays for Continual Learning

https://github.com/krishkribo/3d_gdm-rson

공식 코드

Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization Networks

https://github.com/krm9c/Meta-Continual-Learning

공식 코드

Meta Continual Learning via Dynamic Programming

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