Papers with Code 아카이브

Incremental Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 22
보존된 평가 기록: 112

Incremental learning aims to develop artificially intelligent systems that can continuously learn to address new tasks from new data while preserving knowledge learned from previously learned tasks.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/gahaalt/continual-learning-with-hypernets

Three scenarios for continual learning

https://github.com/gauthamkrishna-g/ActiveHARNet

ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition

https://github.com/geox-lab/cmn

Learning without Forgetting

https://github.com/gmum/hint

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

https://github.com/gmum/hyperinterval

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

https://github.com/hengxyz/ExpressionGAN

ExprGAN: Facial Expression Editing with Controllable Expression Intensity

https://github.com/houchengbin/DynWalks

GloDyNE: Global Topology Preserving Dynamic Network Embedding

https://github.com/hs-jiang/FISVDD

Fast Incremental SVDD Learning Algorithm with the Gaussian Kernel

https://github.com/hshustc/CVPR19_Incremental_Learning

https://github.com/hursung1/GradientEpisodicMemory

Gradient Episodic Memory for Continual Learning

https://github.com/icoz69/cec-cvpr2021

Few-Shot Incremental Learning with Continually Evolved Classifiers

https://github.com/iemprog/mimi

Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation

https://github.com/ihaeyong/SoftNet-3DLS

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

https://github.com/ihaeyong/pnr

Continual Learning: Forget-free Winning Subnetworks for Video Representations

https://github.com/ivclab/cvs

Learning without Forgetting

https://github.com/jacobzhaoziyuan/DSAL

Deeply Supervised Active Learning for Finger Bones Segmentation

https://github.com/jiahuadong/fiss

No One Left Behind: Real-World Federated Class-Incremental Learning

https://github.com/jie-su/bpd

Energy-based Latent Aligner for Incremental Learning

https://github.com/jindongwang/deep-learning-activity-recognition

Deep Learning for Sensor-based Activity Recognition: A Survey

https://github.com/jozhang97/side-tuning

Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks

https://github.com/juntingzh/incremental-learning-baselines

Class-incremental Learning via Deep Model Consolidation

https://github.com/jxcodetw/stylebank

StyleBank: An Explicit Representation for Neural Image Style Transfer

https://github.com/kamsyn95/CL_DNN

Overcoming catastrophic forgetting in neural networks

https://github.com/kimjeyoung/Mahalanobis-BERT

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

https://github.com/kshmelkov/incremental_detectors

Incremental Learning of Object Detectors without Catastrophic Forgetting

https://github.com/lalithjets/domain-adaptation-in-mtl

End-to-End Incremental Learning

https://github.com/lalithjets/domain-generalization-for-surgical-scene-graph

End-to-End Incremental Learning

https://github.com/lamda-cl/revisitingcil

Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need

https://github.com/lancopku/avg-avg

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

https://github.com/llzlcl/Continual-Learning

Three scenarios for continual learning

https://github.com/lofrienger/onetomany_toolsynseg

Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need

https://github.com/mikekestemont/anthem

MBT: A Memory-Based Part of Speech Tagger-Generator

https://github.com/mindspore-ai/contrib/blob/master/application/EWC-Overcoming-catastrophic-forgetting/demo.ipynb

Overcoming catastrophic forgetting in neural networks

https://github.com/mu-y/lll-tts

Overcoming catastrophic forgetting in neural networks

https://github.com/neuraptic/cpe-clip

Multimodal Parameter-Efficient Few-Shot Class Incremental Learning

https://github.com/ngailapdi/LWF

Learning without Forgetting

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