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/1998v7/item

공식 코드

Debiased Sample Selection for Combating Noisy Labels

https://github.com/1998v7/self-filtering

공식 코드

Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization

https://github.com/BaeHeeSun/NPC

공식 코드

From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model

https://github.com/BaeHeeSun/RENT

공식 코드

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

https://github.com/Bidur-Khanal/imbalanced-medical-active-label-cleaning

공식 코드

Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise

https://github.com/ContrastToDivide/C2D

공식 코드

Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels

https://github.com/HanxunH/Active-Passive-Losses

공식 코드

Normalized Loss Functions for Deep Learning with Noisy Labels

https://github.com/Hua-YS/Multi-Scene-Recognition

공식 코드

MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images

https://github.com/KentoNishi/Augmentation-for-LNL

공식 코드

Augmentation Strategies for Learning with Noisy Labels

https://github.com/KevinCarpricorn/EchoAlign

공식 코드

Can We Treat Noisy Labels as Accurate?

https://github.com/Kthyeon/FINE_official

공식 코드

FINE Samples for Learning with Noisy Labels

https://github.com/LiJunnan1992/DivideMix

공식 코드

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

https://github.com/LiJunnan1992/MLNT

공식 코드

Learning to Learn from Noisy Labeled Data

https://github.com/MitchellKT/Enhanced-Meta-Label-Correction

공식 코드

Enhanced Meta Label Correction for Coping with Label Corruption

https://github.com/MrChenFeng/SSR_BMVC2022

공식 코드

SSR: An Efficient and Robust Framework for Learning with Unknown Label Noise

https://github.com/Newbeeer/L_DMI

공식 코드

L_DMI: An Information-theoretic Noise-robust Loss Function

https://github.com/UCSC-REAL/HOC

공식 코드

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels

https://github.com/UCSC-REAL/cores

공식 코드

Learning with Instance-Dependent Label Noise: A Sample Sieve Approach

https://github.com/YisenWang/symmetric_cross_entropy_for_noisy_labels

공식 코드

Symmetric Cross Entropy for Robust Learning with Noisy Labels

https://github.com/YutingLi0606/SURE

공식 코드

SURE: SUrvey REcipes for building reliable and robust deep networks

https://github.com/ZhaoweiZhu1995/HOC

공식 코드

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels

https://github.com/aimagelab/mammoth

공식 코드

May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels

https://github.com/allegro/allenoise

공식 코드

AlleNoise: large-scale text classification benchmark dataset with real-world label noise

https://github.com/anasedova/agra

공식 코드

Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal

https://github.com/ashfarhangi/Protoformer

공식 코드

Protoformer: Embedding Prototypes for Transformers

https://github.com/bbrattoli/JigsawPuzzlePytorch

공식 코드

Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining

https://github.com/bhanML/Co-teaching

공식 코드

Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

https://github.com/btsmart/bootstrapping-label-noise

공식 코드

Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels

https://github.com/bupt-ai-cz/HSA-NRL

공식 코드

Hard Sample Aware Noise Robust Learning for Histopathology Image Classification

https://github.com/bupt-ai-cz/PGDF

공식 코드

Sample Prior Guided Robust Model Learning to Suppress Noisy Labels

https://github.com/changwxx/csot-for-lnl

공식 코드

CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels

https://github.com/chenchenzong/dpc

공식 코드

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels

https://github.com/chengtan9907/co-training-based_noisy-label-learning

공식 코드

Co-learning: Learning from Noisy Labels with Self-supervision

https://github.com/chenpf1025/RobustnessAccuracy

공식 코드

Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels

https://github.com/cityu-aim-group/jcas

공식 코드

Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels

https://github.com/cleanlab/cleanlab

공식 코드

Confident Learning: Estimating Uncertainty in Dataset Labels

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