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/pulp-platform/fscil

공식 코드

12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning

https://github.com/pulp-platform/pulp-trainlib

공식 코드

Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllers

https://github.com/qinyongchun/pearl

공식 코드

PEARL: Input-Agnostic Prompt Enhancement with Negative Feedback Regulation for Class-Incremental Learning

https://github.com/queuq/ms-gode

공식 코드

Learning System Dynamics without Forgetting

https://github.com/qwrawq/segacil

공식 코드

SegACIL: Solving the Stability-Plasticity Dilemma in Class-Incremental Semantic Segmentation

https://github.com/qznan/spankl

공식 코드

A Neural Span-Based Continual Named Entity Recognition Model

https://github.com/radinyn/satsom

공식 코드

Saturation Self-Organizing Map

https://github.com/ragavvenkatesan/Incremental-GAN

공식 코드

A Strategy for an Uncompromising Incremental Learner

https://github.com/rahafaljundi/Gradient-based-Sample-Selection

공식 코드

Gradient based sample selection for online continual learning

https://github.com/rahafaljunditme/continual-novelty-detection

공식 코드

Continual Novelty Detection

https://github.com/rahul13ramesh/modelzoo_continual

공식 코드

Model Zoo: A Growing "Brain" That Learns Continually

https://github.com/raian08/lw2g

공식 코드

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

https://github.com/raincleared-song/conpet

공식 코드

ConPET: Continual Parameter-Efficient Tuning for Large Language Models

https://github.com/raipranav/fcl-fedseit

공식 코드

Federated Continual Learning for Text Classification via Selective Inter-client Transfer

https://github.com/raivnlab/fluid

공식 코드

FLUID: A Unified Evaluation Framework for Flexible Sequential Data

https://github.com/ramakanth-pasunuru/CAS-MAS

공식 코드

Continual and Multi-Task Architecture Search

https://github.com/ranpac/ranpac

공식 코드

RanPAC: Random Projections and Pre-trained Models for Continual Learning

https://github.com/rasvob/hoeffding-trees-with-cpd-multistep-forecasing

공식 코드

A Natural Gas Consumption Forecasting System for Continual Learning Scenarios based on Hoeffding Trees with Change Point Detection Mechanism

https://github.com/raymondchua/simple_successor_features

공식 코드

Learning Successor Features the Simple Way

https://github.com/rehg-lab/CLRec

공식 코드

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

https://github.com/renaisscode/engine

공식 코드

External Knowledge Injection for CLIP-Based Class-Incremental Learning

https://github.com/restrada1/continual-learning

공식 코드

Self-Net: Lifelong Learning via Continual Self-Modeling

https://github.com/rezaakb/peft-vit

공식 코드

Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting

https://github.com/rhe502/icml25-dpcr

공식 코드

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

https://github.com/riyadRafiq/wearable-latent-embedding-exploitation

공식 코드

Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitation

https://github.com/roadonep/eccv2024_mbs

공식 코드

Mitigating Background Shift in Class-Incremental Semantic Segmentation

https://github.com/robertcsordas/linear_layer_as_attention

공식 코드

The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention

https://github.com/robin-karlsson0/dslp

공식 코드

Learning to Predict Navigational Patterns from Partial Observations

https://github.com/robin-karlsson0/predictive-world-models

공식 코드

Predictive World Models from Real-World Partial Observations

https://github.com/robot-learning-freiburg/CoDEPS

공식 코드

CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation

https://github.com/rolsheng/mm-vufm4ds

공식 코드

Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives

https://github.com/rostami-m/ldacid

공식 코드

Continuous Unsupervised Domain Adaptation Using Stabilized Representations and Experience Replay

https://github.com/ruidaniel/rbaca

공식 코드

Continual Deep Active Learning for Medical Imaging: Replay-Base Architecture for Context Adaptation

https://github.com/rvl-lab-utoronto/bfp

공식 코드

Preserving Linear Separability in Continual Learning by Backward Feature Projection

https://github.com/s4nyam/cqural

공식 코드

CQural: A Novel CNN based Hybrid Architecture for Quantum Continual Machine Learning

https://github.com/saehyung-lee/dcc

공식 코드

Dataset Condensation with Contrastive Signals

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