Papers with Code 아카이브

Class Incremental Learning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 3
평가표: 6
보존된 평가 기록: 14

Incremental learning of a sequence of tasks when the task-ID is not available at test time.

코드

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

https://github.com/haseebs/Pseudo-rehearsal-Incremental-Learning

iCaRL: Incremental Classifier and Representation Learning

https://github.com/hooman650/supcl-seq

Supervised Contrastive Learning

https://github.com/hshustc/CVPR19_Incremental_Learning

https://github.com/hursung1/DeepGenerativeReplay

Continual Learning with Deep Generative Replay

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/ilyassmoummad/ProtoCLR

Supervised Contrastive Learning

https://github.com/ivclab/cvs

Learning without Forgetting

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/juntingzh/incremental-learning-baselines

Class-incremental Learning via Deep Model Consolidation

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/kuc2477/pytorch-deep-generative-replay

Continual Learning with Deep Generative Replay

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/lrzpellegrini/CL-CORe-App

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

https://github.com/lrzpellegrini/Fine-Grained-Continual-Learning

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

https://github.com/lrzpellegrini/avalanche

Avalanche: an End-to-End Library for Continual Learning

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

Overcoming catastrophic forgetting in neural networks

https://github.com/mostafaelaraby/bacs-continual-semantic-segmentation

PLOP: Learning without Forgetting for Continual Semantic Segmentation

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

https://github.com/nvshrao/Elastic-Weight-Consolidation

Overcoming catastrophic forgetting in neural networks

https://github.com/paddorch/SupContrast.paddle

Supervised Contrastive Learning

https://github.com/raymin0223/self-contrastive-learning

Supervised Contrastive Learning

https://github.com/renato145/ContrastiveLoss

Supervised Contrastive Learning

https://github.com/rokmr/TACLE

TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning

https://github.com/sairin1202/BIC

Large Scale Incremental Learning

https://github.com/salarim/Semi-Supervised-CL

Supervised Contrastive Learning

https://github.com/sayakpaul/Supervised-Constrastive-Learning-in-TensorFlow-2

Supervised Contrastive Learning

https://github.com/shivamsaboo17/overcoming-catastrophic-forgetting-in-neural-networks

Overcoming catastrophic forgetting in neural networks

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