https://github.com/giacomo-cgn/cmp
공식 코드Replay-free Online Continual Learning with Self-Supervised MultiPatches
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/giangnguyen2412/dissect_catastrophic_forgetting
공식 코드Explaining How Deep Neural Networks Forget by Deep Visualization
https://github.com/giantjun/cl_pytorch
공식 코드Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases
https://github.com/glamor-usc/climb
공식 코드CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
https://github.com/gmum/cw-talar
공식 코드Target Layer Regularization for Continual Learning Using Cramer-Wold Generator
https://github.com/gmum/hint
공식 코드HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
https://github.com/gmum/hyperinterval
공식 코드HINT: Hypernetwork Approach to Training Weight Interval Regions in Continual Learning
https://github.com/gmum/hypermask
공식 코드HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning
https://github.com/gmum/icicle
공식 코드https://github.com/gmum/intercontinet
공식 코드Continual Learning with Guarantees via Weight Interval Constraints
https://github.com/google-research/google-research/tree/master/muNet
공식 코드An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
https://github.com/google-research/google-research/tree/master/supcon
공식 코드https://github.com/google-research/l2p
공식 코드https://github.com/gqk/lae
공식 코드A Unified Continual Learning Framework with General Parameter-Efficient Tuning
https://github.com/grasp-lyrl/modelzoo_continual
공식 코드https://github.com/gregoirepetit/fetril
공식 코드FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
https://github.com/grypesc/adagauss
공식 코드Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
https://github.com/grypesc/camp
공식 코드Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
https://github.com/grypesc/seed
공식 코드Divide and not forget: Ensemble of selectively trained experts in Continual Learning
https://github.com/gt-ripl/coda-prompt
공식 코드CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning
https://github.com/gt-ripl/ftp
공식 코드https://github.com/guiomarpescador/vips
공식 코드Adjusting Model Size in Continual Gaussian Processes: How Big is Big Enough?
https://github.com/gulzainali98/LGCL
공식 코드Introducing Language Guidance in Prompt-based Continual Learning
https://github.com/gurkirt/3D-RetinaNet
공식 코드ROAD: The ROad event Awareness Dataset for Autonomous Driving
https://github.com/gurkirt/road-dataset
공식 코드ROAD: The ROad event Awareness Dataset for Autonomous Driving
https://github.com/guruprasad93/flexiblemachinelearning
공식 코드Engineering flexible machine learning systems by traversing functionally-invariant paths
https://github.com/gvalvano/adversarial-test-time-training
공식 코드Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
https://github.com/gydpku/gsa
공식 코드Dealing with Cross-Task Class Discrimination in Online Continual Learning
https://github.com/gyhandy/channel-wise-lightweight-reprogramming
공식 코드CLR: Channel-wise Lightweight Reprogramming for Continual Learning
https://github.com/habibslim/dkt-for-cil
공식 코드Dataset Knowledge Transfer for Class-Incremental Learning without Memory
https://github.com/haiv-lab/ssiat
공식 코드Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
https://github.com/hamedhemati/cir
공식 코드https://github.com/hamedhemati/omsi
공식 코드Sample Weight Estimation Using Meta-Updates for Online Continual Learning
https://github.com/hamedhemati/partial-hypernetworks-for-cl
공식 코드https://github.com/hankyul2/viewbatchmodel
공식 코드https://github.com/hannibal046/scale
공식 코드SCALE: Synergized Collaboration of Asymmetric Language Translation Engines
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.