Papers with Code 아카이브

Learning with noisy labels

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 0
평가표: 20
보존된 평가 기록: 194

Learning with noisy labels means When we say "noisy labels," we mean that an adversary has intentionally messed up the labels, which would have come from a "clean" distribution otherwise. This setting can also be used to cast learning from only positive and unlabeled data.

코드

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

https://github.com/deepmind/deepmind-research

공식 코드

An Instance-Dependent Simulation Framework for Learning with Label Noise

https://github.com/eden500/Noisy-Labels-Instance-Segmentation

공식 코드

Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters

https://github.com/erikenglesson/gjs

공식 코드

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

https://github.com/facebookresearch/noisy_few_shot

공식 코드

Few-shot Learning with Noisy Labels

https://github.com/fbladl/nvum

공식 코드

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification

https://github.com/federatedml/fedln

공식 코드

Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels

https://github.com/filipe-research/LongReMix

공식 코드

LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment

https://github.com/filipe-research/anne

공식 코드

ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labels

https://github.com/filipe-research/propmix

공식 코드

PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels

https://github.com/fuxiailab/protosemi

공식 코드

Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective

https://github.com/giorgiop/loss-correction

공식 코드

Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach

https://github.com/google-research/sam

공식 코드

Sharpness-Aware Minimization for Efficiently Improving Generalization

https://github.com/google-research/scenic

공식 코드

Learning with Neighbor Consistency for Noisy Labels

https://github.com/haolsun/WarPI

공식 코드

Learning to Rectify for Robust Learning with Noisy Labels

https://github.com/hcyang-null/mild

공식 코드

MILD: Modeling the Instance Learning Dynamics for Learning with Noisy Labels

https://github.com/hhhhhhao/general-framework-weak-supervision

공식 코드

Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations

https://github.com/hitcszx/ALFs

공식 코드

Asymmetric Loss Functions for Learning with Noisy Labels

https://github.com/hitcszx/lnl_sr

공식 코드

Learning with Noisy Labels via Sparse Regularization

https://github.com/hongxin001/JoCoR

공식 코드

Combating noisy labels by agreement: A joint training method with co-regularization

https://github.com/hongxin001/ODNL

공식 코드

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise

https://github.com/hrayrhar/limit-label-memorization

공식 코드

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

https://github.com/hyperconnect/fasten

공식 코드

Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection

https://github.com/hzzone/tcl

공식 코드

Twin Contrastive Learning with Noisy Labels

https://github.com/ican-szu/lond-drs

공식 코드

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

https://github.com/ilonafan/dar-noisy-labels

공식 코드

Exploring Video-Based Driver Activity Recognition under Noisy Labels

https://github.com/inezyu0928/in-context-learning

공식 코드

Exploring the Robustness of In-Context Learning with Noisy Labels

https://github.com/jhoon-oh/kd_data

공식 코드

Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation

https://github.com/jiangwenj02/dynamic_loss

공식 코드

Dynamic Loss For Robust Learning

https://github.com/jiarunliu/co-correcting

공식 코드

Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction

https://github.com/jonathanwilton/RobustDecisionTrees

공식 코드

Robust Loss Functions for Training Decision Trees with Noisy Labels

https://github.com/justherozen/promix

공식 코드

ProMix: Combating Label Noise via Maximizing Clean Sample Utility

https://github.com/lfb-1/gnl

공식 코드

Partial Label Supervision for Agnostic Generative Noisy Label Learning

https://github.com/lijichang/flnl-feddiv

공식 코드

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

https://github.com/lijichang/lnl-nce

공식 코드

Neighborhood Collective Estimation for Noisy Label Identification and Correction

https://github.com/liyi01827/noisy-contrastive

공식 코드

On Learning Contrastive Representations for Learning with Noisy Labels

https://github.com/lxysl/plremix

공식 코드

PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learning

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