Papers with Code 아카이브
Learning with noisy labels
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Fine-Grained Classification with Noisy Labels
Latent Class-Conditional Noise Model
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels
Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels
Model and Data Agreement for Learning with Noisy Labels
Dynamic Loss For Robust Learning
Blind Knowledge Distillation for Robust Image Classification
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method
SplitNet: Learnable Clean-Noisy Label Splitting for Learning with Noisy Labels
Learning with Noisy Labels over Imbalanced Subpopulations
Learning advisor networks for noisy image classification
Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels
Semantic Segmentation with Active Semi-Supervised Representation Learning
Instance-Dependent Noisy Label Learning via Graphical Modelling
Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization
Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels
Neighborhood Collective Estimation for Noisy Label Identification and Correction
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
Towards Harnessing Feature Embedding for Robust Learning with Noisy Labels
Compressing Features for Learning with Noisy Labels
Protoformer: Embedding Prototypes for Transformers
Joint Class-Affinity Loss Correction for Robust Medical Image Segmentation with Noisy Labels
To Aggregate or Not? Learning with Separate Noisy Labels
Communication-Efficient Robust Federated Learning with Noisy Labels
Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages
FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels
Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels
Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.