https://github.com/sahagobinda/CL_PCA
공식 코드SPACE: Structured Compression and Sharing of Representational Space for Continual Learning
Papers with Code 아카이브
Continual Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/sahagobinda/GPM
공식 코드https://github.com/sahagobinda/epr
공식 코드Saliency Guided Experience Packing for Replay in Continual Learning
https://github.com/sahagobinda/sgp
공식 코드https://github.com/sakshi09ch/codec
공식 코드CoDeC: Communication-Efficient Decentralized Continual Learning
https://github.com/salehmomeni/klda
공식 코드Continual Learning Using a Kernel-Based Method Over Foundation Models
https://github.com/sanaAyrml/Class-Impresion-for-Data-free-Incremental-Learning
공식 코드https://github.com/sanketvmehta/lifelong-learning-pretraining-and-sam
공식 코드An Empirical Investigation of the Role of Pre-training in Lifelong Learning
https://github.com/sayantanauddy/clfd
공식 코드https://github.com/sbdzdz/disco
공식 코드Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
https://github.com/sbdzdz/idsprites
공식 코드Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization
https://github.com/scakc/NPBCL
공식 코드https://github.com/scarlet0703/LoRA-Sub-DRS
공식 코드LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
https://github.com/scok30/mae-cil
공식 코드Masked Autoencoders are Efficient Class Incremental Learners
https://github.com/scok30/tass
공식 코드Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning
https://github.com/scok30/vit-cil
공식 코드Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class Incremental Learning
https://github.com/scottgigante/m-phate
공식 코드https://github.com/sebastianbergner/exploringclfd
공식 코드https://github.com/seblee97/student_teacher_catastrophic
공식 코드Continual Learning in the Teacher-Student Setup: Impact of Task Similarity
https://github.com/sein-kim/teracon
공식 코드https://github.com/sethnabarro/gbp_learning
공식 코드Learning in Deep Factor Graphs with Gaussian Belief Propagation
https://github.com/seungyoon-choi/dslr_official
공식 코드DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learning
https://github.com/shahariel/TEAL
공식 코드TEAL: New Selection Strategy for Small Buffers in Experience Replay Class Incremental Learning
https://github.com/shaoyijia/vag
공식 코드https://github.com/sharathraparthy/polynomial-mixing-times
공식 코드Continual Learning In Environments With Polynomial Mixing Times
https://github.com/shibhansh/loss-of-plasticity
공식 코드https://github.com/shinhwankang/begin
공식 코드BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
https://github.com/shiningsunnyday/ucl
공식 코드Improving Representational Continuity via Continued Pretraining
https://github.com/shirowalker/ucad
공식 코드Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt
https://github.com/showlab/clvqa
공식 코드Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task
https://github.com/showlab/efficient-cls
공식 코드Label-Efficient Online Continual Object Detection in Streaming Video
https://github.com/shuvenduroy/coact-fscil
공식 코드Few-shot Tuning of Foundation Models for Class-incremental Learning
https://github.com/siat-nlp/TPEM
공식 코드https://github.com/sidak/otfusion
공식 코드https://github.com/siddharthverma314/clcp-neurips-2020
공식 코드Continual Learning of Control Primitives: Skill Discovery via Reset-Games
https://github.com/simomagi/elastic_feature_consolidation
공식 코드Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.