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/fanyan0411/dsgd
공식 코드Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
https://github.com/feifeiobama/InfluenceCL
공식 코드https://github.com/felixhuiweilin/pcr
공식 코드PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning
https://github.com/ferdinandzju/iap
공식 코드IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting
https://github.com/fexed/clforhsm
공식 코드https://github.com/feyzaakyurek/subspace-reg
공식 코드Subspace Regularizers for Few-Shot Class Incremental Learning
https://github.com/firatozdemir/LwfSeg-AeiSeg
공식 코드Extending Pretrained Segmentation Networks with Additional Anatomical Structures
https://github.com/firefyf/scrollnet
공식 코드https://github.com/firehose-dataset/congrad
공식 코드Drinking from a Firehose: Continual Learning with Web-scale Natural Language
https://github.com/fischer-tom/inemo
공식 코드iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning
https://github.com/fishercats/clg-cbm
공식 코드Language Guided Concept Bottleneck Models for Interpretable Continual Learning
https://github.com/flairox/behaviour-distillation
공식 코드https://github.com/fostiropoulos/stream_benchmark
공식 코드Batch Model Consolidation: A Multi-Task Model Consolidation Framework
https://github.com/foundationagents/awesome-foundation-agents
공식 코드https://github.com/francesco-p/off-the-shelf-cl
공식 코드Simpler is Better: off-the-shelf Continual Learning Through Pretrained Backbones
https://github.com/freedbee/continual_regularisation
공식 코드https://github.com/fszatkowski/cl-teacher-adaptation
공식 코드Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
https://github.com/ftraeuble/experiments_discrete_key_value_bottleneck
공식 코드https://github.com/fulin-gao/opengcd
공식 코드OpenGCD: Assisting Open World Recognition with Generalized Category Discovery
https://github.com/funz-0/one-for-more
공식 코드One-for-More: Continual Diffusion Model for Anomaly Detection
https://github.com/fwu11/macil
공식 코드Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning
https://github.com/g-u-n/pycil
공식 코드https://github.com/gabriel-skantze/CoLLIE
공식 코드CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings
https://github.com/ganglii/devsafety
공식 코드A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety
https://github.com/ganguli-lab/pathint
공식 코드https://github.com/gaojingsheng/lamm
공식 코드https://github.com/gargrohin/amat
공식 코드Overcoming Mode Collapse with Adaptive Multi Adversarial Training
https://github.com/gawainxu/openincremen
공식 코드OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning
https://github.com/gdkent/bsg_methods_con_unc
공식 코드Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems
https://github.com/gdubbs100/right_left_brain_rl
공식 코드https://github.com/genentech/branched-diffusion
공식 코드Hierarchically branched diffusion models leverage dataset structure for class-conditional generation
https://github.com/gengdavid/slca
공식 코드SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
https://github.com/gerdm/BONE
공식 코드A unifying framework for generalised Bayesian online learning in non-stationary environments
https://github.com/ghy0501/awesome-continual-learning-in-generative-models
공식 코드A Comprehensive Survey on Continual Learning in Generative Models
https://github.com/ghy0501/pilora
공식 코드PILoRA: Prototype Guided Incremental LoRA for Federated Class-Incremental Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.