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/neu-spiral/SparCL

공식 코드

SparCL: Sparse Continual Learning on the Edge

https://github.com/neurai-lab/bio-ann

공식 코드

A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning

https://github.com/neurai-lab/birt

공식 코드

BiRT: Bio-inspired Replay in Vision Transformers for Continual Learning

https://github.com/neurai-lab/consistencycl

공식 코드

Consistency is the key to further mitigating catastrophic forgetting in continual learning

https://github.com/neurai-lab/cude-monodepthcl

공식 코드

Continual Learning of Unsupervised Monocular Depth from Videos

https://github.com/neurai-lab/dynamiccontinuallearning

공식 코드

Dynamically Modular and Sparse General Continual Learning

https://github.com/neurai-lab/esmer

공식 코드

Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

https://github.com/neurai-lab/imex-reg

공식 코드

IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning

https://github.com/neurai-lab/scommer

공식 코드

Sparse Coding in a Dual Memory System for Lifelong Learning

https://github.com/neurai-lab/synergy

공식 코드

SYNERgy between SYNaptic consolidation and Experience Replay for general continual learning

https://github.com/neurai-lab/tamil

공식 코드

Task-Aware Information Routing from Common Representation Space in Lifelong Learning

https://github.com/neurai-lab/tarc

공식 코드

Task Agnostic Representation Consolidation: a Self-supervised based Continual Learning Approach

https://github.com/neuralcollapseapplications/unicil

공식 코드

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

https://github.com/neurodata/SDTF

공식 코드

Simplest Streaming Trees

https://github.com/ngailapdi/CLRec

공식 코드

The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction

https://github.com/nhiratani/transfer_retention_model

공식 코드

Disentangling and Mitigating the Impact of Task Similarity for Continual Learning

https://github.com/nicolas1203/mkd_ocl

공식 코드

Rethinking Momentum Knowledge Distillation in Online Continual Learning

https://github.com/nicolas1203/ocl-fd

공식 코드

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

https://github.com/nicolas1203/ossgcl

공식 코드

Contrastive Learning for Online Semi-Supervised General Continual Learning

https://github.com/nik-dim/sequel

공식 코드

SequeL: A Continual Learning Library in PyTorch and JAX

https://github.com/nju-rl/cugro

공식 코드

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay

https://github.com/nlpie-research/compact-biomedical-transformers

공식 코드

On the Effectiveness of Compact Biomedical Transformers

https://github.com/nlpie-research/lightweight-clinical-transformers

공식 코드

Lightweight Transformers for Clinical Natural Language Processing

https://github.com/noorahmedds/orco

공식 코드

OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

https://github.com/nourhanb/biaspruner

공식 코드

BiasPruner: Debiased Continual Learning for Medical Image Classification

https://github.com/numenta/htmpapers

공식 코드

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments

https://github.com/numone01/categorizer

공식 코드

Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery

https://github.com/nurikorhan/negotiated-representations

공식 코드

Negotiated Representations for Machine Mearning Application

https://github.com/nurikorhan/negotiated-representations-for-continual-learning

공식 코드

Negotiated Representations to Prevent Forgetting in Machine Learning Applications

https://github.com/nvcuong/variational-continual-learning

공식 코드

Improving and Understanding Variational Continual Learning

https://github.com/ocram17/gcab-cfdc

공식 코드

Exemplar-free Continual Learning of Vision Transformers via Gated Class-Attention and Cascaded Feature Drift Compensation

https://github.com/oleksost/latent_cl

공식 코드

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

https://github.com/oleksost/lmc

공식 코드

Continual Learning via Local Module Composition

https://github.com/om-ai-lab/OmDet

공식 코드

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network

https://github.com/omegafragger/ldifs_code

공식 코드

Fine-tuning can cripple your foundation model; preserving features may be the solution

https://github.com/omnia-unist/Miro

공식 코드

Cost-effective On-device Continual Learning over Memory Hierarchy with Miro

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