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.
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
Distilling effective supervision for robust medical image segmentation with noisy labels
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
To Smooth or Not? When Label Smoothing Meets Noisy Labels
Asymmetric Loss Functions for Learning with Noisy Labels
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation
Joint Text and Label Generation for Spoken Language Understanding
Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
Faster Meta Update Strategy for Noise-Robust Deep Learning
Boosting Co-teaching with Compression Regularization for Label Noise
MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
Transform consistency for learning with noisy labels
Co-matching: Combating Noisy Labels by Augmentation Anchoring
On the Robustness of Monte Carlo Dropout Trained with Noisy Labels
Learning with Group Noise
Learning with Feature-Dependent Label Noise: A Progressive Approach
NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
Unified Robust Training for Graph NeuralNetworks against Label Noise
Augmentation Strategies for Learning with Noisy Labels
DST: Data Selection and joint Training for Learning with Noisy Labels
FINE Samples for Learning with Noisy Labels
Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Understanding Instance-Level Label Noise: Disparate Impacts and Treatments
Provably End-to-end Label-Noise Learning without Anchor Points
Towards Robustness to Label Noise in Text Classification via Noise Modeling
Unsupervised Domain Adaptation of Black-Box Source Models
Robust Collaborative Learning with Noisy Labels
How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?
A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?
Robust Federated Learning with Noisy Labels
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.