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/doubleclass/gmm
공식 코드Generative Multi-modal Models are Good Class-Incremental Learners
https://github.com/dr-bell/kaizen
공식 코드Kaizen: Practical Self-supervised Continual Learning with Continual Fine-tuning
https://github.com/drimpossible/acm
공식 코드https://github.com/drimpossible/budgetcl
공식 코드Computationally Budgeted Continual Learning: What Does Matter?
https://github.com/drimpossible/evalocl
공식 코드Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
https://github.com/drimpossible/randumb
공식 코드Random Representations Outperform Online Continually Learned Representations
https://github.com/dtuzi123/ovae
공식 코드Continual Variational Autoencoder Learning via Online Cooperative Memorization
https://github.com/duguodong7/graftllm
공식 코드https://github.com/dyxu-cuhkcse/smg-learning
공식 코드https://github.com/eaaguilart/cedl
공식 코드Continual Evidential Deep Learning for Out-of-Distribution Detection
https://github.com/eleutherai/gpt-neox
공식 코드Simple and Scalable Strategies to Continually Pre-train Large Language Models
https://github.com/elfsong/dynamind
공식 코드From Static to Dynamic: A Continual Learning Framework for Large Language Models
https://github.com/elifcerengokyildirim/adacl
공식 코드https://github.com/ema-frasca/casper
공식 코드https://github.com/ema-marconato/nesy-cl
공식 코드Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
https://github.com/ennengyang/awesome-forgetting-in-deep-learning
공식 코드A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
https://github.com/ennengyang/awesome-model-merging-methods-theories-applications
공식 코드Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
https://github.com/eric11220/pretrained-models-in-cl
공식 코드Do Pre-trained Models Benefit Equally in Continual Learning?
https://github.com/erummushtaq/cromo-mixup
공식 코드CroMo-Mixup: Augmenting Cross-Model Representations for Continual Self-Supervised Learning
https://github.com/ethancaballero/broken_neural_scaling_laws
공식 코드https://github.com/ethz-asl/background_foreground_segmentation
공식 코드https://github.com/evelynchee/lo2ln
공식 코드Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
https://github.com/explainableml/fomo_in_flux
공식 코드https://github.com/facebookresearch/Adversarial-Continual-Learning
공식 코드https://github.com/facebookresearch/CTrLBenchmark
공식 코드Efficient Continual Learning with Modular Networks and Task-Driven Priors
https://github.com/facebookresearch/GradientEpisodicMemory
공식 코드https://github.com/facebookresearch/GraphLog
공식 코드https://github.com/facebookresearch/ParlAI/tree/main/projects/bb3
공식 코드BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
https://github.com/facebookresearch/agem
공식 코드https://github.com/facebookresearch/dst-egqa
공식 코드Continual Dialogue State Tracking via Example-Guided Question Answering
https://github.com/facebookresearch/egocentricuseradaptation
공식 코드EgoAdapt: A multi-stream evaluation study of adaptation to real-world egocentric user video
https://github.com/facebookresearch/egoobjects
공식 코드EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding
https://github.com/facebookresearch/iSDF
공식 코드iSDF: Real-Time Neural Signed Distance Fields for Robot Perception
https://github.com/facebookresearch/salina
공식 코드Building a Subspace of Policies for Scalable Continual Learning
https://github.com/fagp/sinkhorn-rebasin
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.