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/INK-USC/VG-CCL

공식 코드

Visually Grounded Continual Learning of Compositional Phrases

https://github.com/INK-USC/VisCOLL

공식 코드

Visually Grounded Continual Learning of Compositional Phrases

https://github.com/IemProg/QUAD

공식 코드

No Images, No Problem: Retaining Knowledge in Continual VQA with Questions-Only Memory

https://github.com/JanBerg1/AAC-LwF

공식 코드

Continual Learning for Automated Audio Captioning Using The Learning Without Forgetting Approach

https://github.com/JosephKJ/merlin

공식 코드

Meta-Consolidation for Continual Learning

https://github.com/JoyHuYY1412/DDE_CIL

공식 코드

Distilling Causal Effect of Data in Class-Incremental Learning

https://github.com/JuliousHurtado/MOE

공식 코드

Memory Population in Continual Learning via Outlier Elimination

https://github.com/JuliousHurtado/meta-training-setup

공식 코드

Optimizing Reusable Knowledge for Continual Learning via Metalearning

https://github.com/JunMa11/AbdomenCT-1K

공식 코드

AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?

https://github.com/KamilDeja/multiband_vae

공식 코드

Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning

https://github.com/Karolina-Bogacka/ReReLRP

공식 코드

ReReLRP - Remembering and Recognizing Tasks with LRP

https://github.com/Khurramjaved96/mrcl

공식 코드

Meta-Learning Representations for Continual Learning

https://github.com/KululuMi/RCL

공식 코드

Adversarial Robust Memory-Based Continual Learner

https://github.com/LYang-666/TRGP

공식 코드

TRGP: Trust Region Gradient Projection for Continual Learning

https://github.com/Lee-Gihun/FedNTD

공식 코드

Preservation of the Global Knowledge by Not-True Distillation in Federated Learning

https://github.com/Lee-Gihun/FedSOL

공식 코드

FedSOL: Stabilized Orthogonal Learning with Proximal Restrictions in Federated Learning

https://github.com/MACS-Research-Lab/safe-continual

공식 코드

On the Design of Safe Continual RL Methods for Control of Nonlinear Systems

https://github.com/MECLabTUDA/ACS

공식 코드

Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation

https://github.com/MECLabTUDA/Lifelong-nnUNet

공식 코드

Continual Hippocampus Segmentation with Transformers

https://github.com/MECLabTUDA/NCAdapt

공식 코드

NCAdapt: Dynamic adaptation with domain-specific Neural Cellular Automata for continual hippocampus segmentation

https://github.com/MIFA-Lab/SAFE

공식 코드

SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models

https://github.com/MSNLAB/Federated-Lifelong-Person-ReID

공식 코드

Spatial-Temporal Federated Learning for Lifelong Person Re-identification on Distributed Edges

https://github.com/MSiam/AdaptiveMaskedProxies

공식 코드

Adaptive Masked Proxies for Few-Shot Segmentation

https://github.com/MalvinaNikandrou/contvqa

공식 코드

Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering

https://github.com/MalvinaNikandrou/mafed

공식 코드

Enhancing Continual Learning in Visual Question Answering with Modality-Aware Feature Distillation

https://github.com/Masuyama-lab/FCAC

공식 코드

Privacy-preserving Continual Federated Clustering via Adaptive Resonance Theory

https://github.com/Mattdl/ContinualPrototypeEvolution

공식 코드

Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams

https://github.com/Mattdl/RehearsalRevealed

공식 코드

Rehearsal revealed: The limits and merits of revisiting samples in continual learning

https://github.com/MattiaSangermano/OLCGM

공식 코드

Sample Condensation in Online Continual Learning

https://github.com/MehdiAbbanaBennani/continual-learning-ogdplus

공식 코드

Generalisation Guarantees for Continual Learning with Orthogonal Gradient Descent

https://github.com/MostafaRahgouy/AA-CIL

공식 코드

Towards Effective Authorship Attribution: Integrating Class-Incremental Learning

https://github.com/MrPio/KAN-Continual_Learning_tests

공식 코드

A preliminary study on continual learning in computer vision using Kolmogorov-Arnold Networks

https://github.com/MrtnMndt/OCDVAEContinualLearning

공식 코드

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

https://github.com/MrtnMndt/OCDVAE_ContinualLearning

공식 코드

Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition

https://github.com/NVlabs/DeepInversion

공식 코드

Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion

https://github.com/NeurAI-Lab/AGILE

공식 코드

Mitigating Interference in the Knowledge Continuum through Attention-Guided Incremental Learning

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