Survey
Active Learning班に配属,Data Cleansingについて調査
CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images
Data Cleansing for Models Trained with SGD
Data Cleansing for Deep Neural Networks with Storage-efficient Approximation of Influence Functions
DivideMix: Learning with Noisy Labels as Semi-supervised Learning
FINE Samples for Learning with Noisy Labels
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking
Focal Loss for Dense Object Detection
CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning
PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection
Selective-Supervised Contrastive Learning with Noisy Labels