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/ibm/constrained-fscil

공식 코드

Constrained Few-shot Class-incremental Learning

https://github.com/icans-strasbourg/psat

공식 코드

PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning

https://github.com/iclr2020-apd/anonymous_iclr2020_apd_code

공식 코드

Scalable and Order-robust Continual Learning with Additive Parameter Decomposition

https://github.com/ict-bigdatalab/clever

공식 코드

Continual Learning for Generative Retrieval over Dynamic Corpora

https://github.com/ictnlp/cokd

공식 코드

Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation

https://github.com/ictnlp/lfr-nmt

공식 코드

Continual Learning of Neural Machine Translation within Low Forgetting Risk Regions

https://github.com/idiap/translation-aided-slu

공식 코드

The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation

https://github.com/idsia/automated-cl

공식 코드

Automating Continual Learning

https://github.com/iemprog/cofima

공식 코드

Weighted Ensemble Models Are Strong Continual Learners

https://github.com/ifnspaml/CIL_Segmentation

공식 코드

Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels

https://github.com/igolan/bgd

공식 코드

Task Agnostic Continual Learning Using Online Variational Bayes

https://github.com/ihaeyong/pfnr

공식 코드

Progressive Fourier Neural Representation for Sequential Video Compilation

https://github.com/ihaeyong/pnr

공식 코드

Progressive Fourier Neural Representation for Sequential Video Compilation

https://github.com/ihaeyong/soft-tf

공식 코드

Soft-TransFormers for Continual Learning

https://github.com/ihaeyong/softnet-fscil

공식 코드

On the Soft-Subnetwork for Few-shot Class Incremental Learning

https://github.com/imirzadeh/MC-SGD

공식 코드

Linear Mode Connectivity in Multitask and Continual Learning

https://github.com/imirzadeh/stable-continual-learning

공식 코드

Dropout as an Implicit Gating Mechanism For Continual Learning

https://github.com/imzhangxikun/pdgnns

공식 코드

Topology-aware Embedding Memory for Continual Learning on Expanding Networks

https://github.com/indusolo/unsup_ll

공식 코드

U-TELL: Unsupervised Task Expert Lifelong Learning

https://github.com/innixma/dex

공식 코드

Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning

https://github.com/intellabs/clnerf

공식 코드

CLNeRF: Continual Learning Meets NeRF

https://github.com/intellabs/continuallearning

공식 코드

Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data

https://github.com/intellistream/efficient-stream-learning

공식 코드

StreamFP: Learnable Fingerprint-guided Data Selection for Efficient Stream Learning

https://github.com/isee-laboratory/revisting_fscil

공식 코드

Rethinking Few-shot Class-incremental Learning: Learning from Yourself

https://github.com/ispamm/PRER

공식 코드

Pseudo-Rehearsal for Continual Learning with Normalizing Flows

https://github.com/ivclab/CPG

공식 코드

Compacting, Picking and Growing for Unforgetting Continual Learning

https://github.com/ivclab/cvs

공식 코드

Continual Learning for Visual Search with Backward Consistent Feature Embedding

https://github.com/ivsucram/cdcl

공식 코드

Towards Cross-Domain Continual Learning

https://github.com/ivsucram/cfa

공식 코드

Class-Incremental Learning via Knowledge Amalgamation

https://github.com/jaryP/Cascaded-Scaling-Classifier

공식 코드

Class incremental learning with probability dampening and cascaded gated classifier

https://github.com/jaryP/CentroidsMatching

공식 코드

Centroids Matching: an efficient Continual Learning approach operating in the embedding space

https://github.com/jaryP/Master-thesis

공식 코드

Efficient Continual Learning in Neural Networks with Embedding Regularization

https://github.com/jaryP/StructuredEnsemble

공식 코드

Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods

https://github.com/jaryp/cil-margin-dampening-gated-classifier

공식 코드

Class incremental learning with probability dampening and cascaded gated classifier

https://github.com/jaryp/continual-learning-with-invertible-generative-models

공식 코드

Continual Learning with Invertible Generative Models

https://github.com/jasmine-0/spcl

공식 코드

Towards stable training of parallel continual learning

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