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/online-ml/river

공식 코드

River: machine learning for streaming data in Python

https://github.com/optimass/Maximally_Interfered_Retrieval

공식 코드

Online Continual Learning with Maximally Interfered Retrieval

https://github.com/osu-nlp-group/hipporag

공식 코드

From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

https://github.com/oswaldoludwig/CLASSP

공식 코드

CLASSP: a Biologically-Inspired Approach to Continual Learning through Adjustment Suppression and Sparsity Promotion

https://github.com/panagiotamoraiti/continual-learning-challenge-2024

공식 코드

Technical Report for the 5th CLVision Challenge at CVPR: Addressing the Class-Incremental with Repetition using Unlabeled Data -- 4th Place Solution

https://github.com/pastifra/Continual_Nanodet

공식 코드

Latent Distillation for Continual Object Detection at the Edge

https://github.com/pastifra/TiROD_code

공식 코드

Tiny Robotics Dataset and Benchmark for Continual Object Detection

https://github.com/patrickzad/pops

공식 코드

Prompting Continual Person Search

https://github.com/patrickzh/deepcore

공식 코드

DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

https://github.com/pauljanson002/pretrained-cl

공식 코드

A Simple Baseline that Questions the Use of Pretrained-Models in Continual Learning

https://github.com/pavanteja295/CACL

공식 코드

Compression-aware Continual Learning using Singular Value Decomposition

https://github.com/pbihao/slm

공식 코드

Scalable Language Model with Generalized Continual Learning

https://github.com/pclucas14/adaptive-quantization-modules

공식 코드

Online Learned Continual Compression with Adaptive Quantization Modules

https://github.com/pclucas14/aml

공식 코드

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

https://github.com/pcwhy/CSIL

공식 코드

Class-Incremental Learning for Wireless Device Identification in IoT

https://github.com/pedro-morgado/nettailor

공식 코드

NetTailor: Tuning the Architecture, Not Just the Weights

https://github.com/pefimov/cross-lingual-adjustment

공식 코드

The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer

https://github.com/pepperjao/adaptcl

공식 코드

AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets

https://github.com/phquang/Bilevel-Continual-Learning

공식 코드

Bilevel Continual Learning

https://github.com/phquang/DualNet

공식 코드

DualNet: Continual Learning, Fast and Slow

https://github.com/phquang/continual-normalization

공식 코드

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

https://github.com/phunglai728/dp-cl

공식 코드

Continual Learning with Differential Privacy

https://github.com/pku-yuangroup/n-lora

공식 코드

Is Parameter Collision Hindering Continual Learning in LLMs?

https://github.com/pkuxmq/hlop-snn

공식 코드

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

https://github.com/plai-group/lpr

공식 코드

Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning

https://github.com/plai-group/simple-cnaps

공식 코드

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning

https://github.com/pmorenoz/ContinualGP

공식 코드

Continual Multi-task Gaussian Processes

https://github.com/pmorenoz/continual_ihcpd

공식 코드

Continual Learning for Infinite Hierarchical Change-Point Detection

https://github.com/pnnl/multifidelity_continual_learning

공식 코드

A multifidelity approach to continual learning for physical systems

https://github.com/pokaxpoka/deep_Mahalanobis_detector

공식 코드

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

https://github.com/pranshu28/TAG

공식 코드

TAG: Task-based Accumulated Gradients for Lifelong learning

https://github.com/prasannab29/pacda

공식 코드

Continual Domain Adaptation through Pruning-aided Domain-specific Weight Modulation

https://github.com/prateeky2806/exessnet

공식 코드

Exclusive Supermask Subnetwork Training for Continual Learning

https://github.com/prbonn/shine_mapping

공식 코드

SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations

https://github.com/princetonvisualai/rememberthepast-datasetdistillation

공식 코드

Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks

https://github.com/pulp-bio/bmi-odcl

공식 코드

Train-On-Request: An On-Device Continual Learning Workflow for Adaptive Real-World Brain Machine Interfaces

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