Papers with Code 아카이브
Incremental Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 22
- 보존된 평가 기록
- 112
Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/zhoudw-zdw/PROOF
공식 코드https://github.com/zhoudw-zdw/TPAMI-Limit
공식 코드Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks
https://github.com/zhoudw-zdw/cil_survey
공식 코드A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
https://github.com/zhoudw-zdw/cvpr22-fact
공식 코드https://github.com/zhoudw-zdw/revisitingcil
공식 코드https://github.com/zhoujiahuan1991/aaai2025-caprompt
공식 코드CAPrompt: Cyclic Prompt Aggregation for Pre-Trained Model Based Class Incremental Learning
https://github.com/zhoujiahuan1991/icml2025-ka-prompt
공식 코드Componential Prompt-Knowledge Alignment for Domain Incremental Learning
https://github.com/zhu-gl-ux/adapter
공식 코드Adaptive Prototype Replay for Class Incremental Semantic Segmentation
https://github.com/zhukaii/SPPR
공식 코드Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
https://github.com/zixuanke/pycontinual
공식 코드CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
https://github.com/zoilsen/clom
공식 코드Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
https://github.com/zoilsen/comp-fscil
공식 코드https://github.com/zqiao11/tscil
공식 코드Class-incremental Learning for Time Series: Benchmark and Evaluation
https://github.com/zysong0113/savc
공식 코드https://github.com/zyuh/bdr-main
공식 코드Balanced Destruction-Reconstruction Dynamics for Memory-replay Class Incremental Learning
https://github.com/zzz47zzz/codebase-for-incremental-learning-with-llm
공식 코드Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models
https://github.com/zzz47zzz/pretrained-lm-for-incremental-learning
공식 코드Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models
https://gitlab.com/fildne/fildne
공식 코드FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings
https://gitlab.com/viper-purdue/continual-compression
공식 코드Towards Backward-Compatible Continual Learning of Image Compression
https://gitlab.com/viper-purdue/delta
공식 코드https://gitlab.com/viper-purdue/ocil-real-world-food-image-classification
공식 코드Online Class-Incremental Learning For Real-World Food Image Classification
https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm
공식 코드RMM: Reinforced Memory Management for Class-Incremental Learning
https://gitlab.mpi-klsb.mpg.de/yaoyaoliu/rmm/
공식 코드RMM: Reinforced Memory Management for Class-Incremental Learning
https://github.com/2023-MindSpore-1/ms-code-70
https://github.com/BPfuelb/CF_in_DNNs
https://github.com/CanPeng123/Faster-ILOD
Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN
https://github.com/ContinualAI/avalanche
https://github.com/DRSAD/iCaRL
https://github.com/GMvandeVen/complex-synapses
https://github.com/House-Leo/FoundIR
FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration
https://github.com/HuiDingUMD/ExprGAN
ExprGAN: Facial Expression Editing with Controllable Expression Intensity
https://github.com/Kabir5296/CSTA-CustomImplementation
CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning
https://github.com/King-Of-Knights/overcoming-catastrophic
https://github.com/LTTM/IL-SemSegm
https://github.com/MECLabTUDA/ACS
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.