Papers with Code 아카이브

Continual Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/minhchuyentoancbn/moe_promptcl

공식 코드

Mixture of Experts Meets Prompt-Based Continual Learning

https://github.com/mit-ll/lorax_cil

공식 코드

LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution

https://github.com/mjy1111/prune

공식 코드

Perturbation-Restrained Sequential Model Editing

https://github.com/ml-group-sdu/macro-auc-cl

공식 코드

Towards Macro-AUC oriented Imbalanced Multi-Label Continual Learning

https://github.com/ml-research/CLEVA-Compass

공식 코드

CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability

https://github.com/ml-research/concon

공식 코드

Where is the Truth? The Risk of Getting Confounded in a Continual World

https://github.com/ml-research/confedmade

공식 코드

Masked Autoencoders are Efficient Continual Federated Learners

https://github.com/ml4ai/fed-recon

공식 코드

Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning

https://github.com/mlcolab/psi-kt

공식 코드

Predictive, scalable and interpretable knowledge tracing on structured domains

https://github.com/mli-lab/regularization_based_continual_learning

공식 코드

Provable Continual Learning via Sketched Jacobian Approximations

https://github.com/mlrep/ie-20

공식 코드

Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams

https://github.com/mmasana/FACIL

공식 코드

Class-incremental learning: survey and performance evaluation on image classification

https://github.com/mmderakhshani/KCL

공식 코드

Kernel Continual Learning

https://github.com/mmderakhshani/lifelonger

공식 코드

LifeLonger: A Benchmark for Continual Disease Classification

https://github.com/mnoorfawi/curlora

공식 코드

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation

https://github.com/mohmdelsayed/upgd

공식 코드

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

https://github.com/montrealrobotics/La-MAML

공식 코드

La-MAML: Look-ahead Meta Learning for Continual Learning

https://github.com/moonjunyyy/si-blurry

공식 코드

Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning

https://github.com/morganbdt/crumb

공식 코드

Tuned Compositional Feature Replays for Efficient Stream Learning

https://github.com/mostafaelaraby/bacs-continual-semantic-segmentation

공식 코드

BACS: Background Aware Continual Semantic Segmentation

https://github.com/moukamisama/f2m

공식 코드

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

https://github.com/mrezaim/Expanse

공식 코드

EXPANSE: A Deep Continual / Progressive Learning System for Deep Transfer Learning

https://github.com/mrgiovanni/continuallearning

공식 코드

Continual Learning for Abdominal Multi-Organ and Tumor Segmentation

https://github.com/mrifkikurniawan/sslad

공식 코드

Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification

https://github.com/msrocean/continual-learning-malware

공식 코드

On the Limitations of Continual Learning for Malware Classification

https://github.com/muratonuryildirim/cl-with-dst

공식 코드

Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates

https://github.com/muratonuryildirim/focil

공식 코드

FOCIL: Finetune-and-Freeze for Online Class Incremental Learning by Training Randomly Pruned Sparse Experts

https://github.com/mxu34/mbrl-gpmm

공식 코드

Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes

https://github.com/naderAsadi/AML

공식 코드

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

https://github.com/naderasadi/clhive

공식 코드

Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning

https://github.com/naeem-paeedeh/robusta

공식 코드

Few-Shot Class Incremental Learning via Robust Transformer Approach

https://github.com/naga-karthik/continual-learning-ms

공식 코드

Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?

https://github.com/naver-ai/i-blurry

공식 코드

Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference

https://github.com/naver-ai/seit

공식 코드

SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage

https://github.com/nazmul-karim170/cnll

공식 코드

CNLL: A Semi-supervised Approach For Continual Noisy Label Learning

https://github.com/nchuramani/fcl-mannersdb

공식 코드

Federated Learning of Socially Appropriate Agent Behaviours in Simulated Home Environments

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.