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/apple/ml-tic-clip

공식 코드

TiC-CLIP: Continual Training of CLIP Models

https://github.com/apple/ml-tic-lm

공식 코드

TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining

https://github.com/aprbw/ood_electricity_forecasting_during_covid-19

공식 코드

Navigating Out-of-Distribution Electricity Load Forecasting during COVID-19: Benchmarking energy load forecasting models without and with continual learning

https://github.com/aprilsveryown/semantically-guided-continual-learning

공식 코드

Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning

https://github.com/arazd/ProgressivePrompts

공식 코드

Progressive Prompts: Continual Learning for Language Models

https://github.com/arefaz/e3-ensemble-of-expert-embedders-cvprwmf24

공식 코드

E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data

https://github.com/arslan-chaudhry/orthog_subspace

공식 코드

Continual Learning in Low-rank Orthogonal Subspaces

https://github.com/arthurdouillard/CVPR2021_PLOP

공식 코드

PLOP: Learning without Forgetting for Continual Semantic Segmentation

https://github.com/arthurdouillard/dytox

공식 코드

DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion

https://github.com/arthurdouillard/incremental_learning.pytorch

공식 코드

PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

https://github.com/arunmallya/packnet

공식 코드

PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning

https://github.com/arunmallya/piggyback

공식 코드

Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

https://github.com/arvin0313/mecoin-gfscil

공식 코드

An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning

https://github.com/ashok-arjun/CSCCT

공식 코드

Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer

https://github.com/atenrev/diffusion_continual_learning

공식 코드

Continual Learning of Diffusion Models with Generative Distillation

https://github.com/atenrev/difussion_continual_learning

공식 코드

Continual Learning of Diffusion Models with Generative Distillation

https://github.com/aubreygjh/e-cgl

공식 코드

E-CGL: An Efficient Continual Graph Learner

https://github.com/avalonstrel/mitigating-the-alignment-tax-of-rlhf

공식 코드

Mitigating the Alignment Tax of RLHF

https://github.com/awarelab/continual_world

공식 코드

Continual World: A Robotic Benchmark For Continual Reinforcement Learning

https://github.com/awjuliani/deep-rl-plasticity

공식 코드

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning

https://github.com/awslabs/renate

공식 코드

Renate: A Library for Real-World Continual Learning

https://github.com/azizanlab/sketchogd

공식 코드

SketchOGD: Memory-Efficient Continual Learning

https://github.com/badripatro/efficient360

공식 코드

Efficiency 360: Efficient Vision Transformers

https://github.com/bahuia/sscl-text2sql

공식 코드

Learn from Yesterday: A Semi-Supervised Continual Learning Method for Supervision-Limited Text-to-SQL Task Streams

https://github.com/baithebest/samc

공식 코드

Saliency-Augmented Memory Completion for Continual Learning

https://github.com/baithebest/sharc

공식 코드

Saliency-Guided Hidden Associative Replay for Continual Learning

https://github.com/banafsheh-rafiee/From-Eye-blinks-to-State-Construction-Diagnostic-Benchmarks-for-Online-Representation-Learning

공식 코드

From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning

https://github.com/beijixiong3510/OWM

공식 코드

Continual Learning of Context-dependent Processing in Neural Networks

https://github.com/berkeleyautomation/ifl_benchmark

공식 코드

Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision

https://github.com/bessagroup/cddm

공식 코드

Cooperative data-driven modeling

https://github.com/beyonderxx/trace

공식 코드

TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

https://github.com/bigdata-inha/Split-and-Bridge

공식 코드

Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network

https://github.com/bigdata-inha/recall-oriented-cl-framework

공식 코드

Recall-Oriented Continual Learning with Generative Adversarial Meta-Model

https://github.com/biomedia-mbzuai/awesome-cl-in-medical

공식 코드

Continual Learning in Medical Imaging: A Survey and Practical Analysis

https://github.com/biomedia-mbzuai/dynammo

공식 코드

DynaMMo: Dynamic Model Merging for Efficient Class Incremental Learning for Medical Images

https://github.com/biqing-qi/interactive-continual-learning-fast-and-slow-thinking

공식 코드

Interactive Continual Learning: Fast and Slow Thinking

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