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

H Wei, L Feng, X Chen, B An - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
Deep Learning with noisy labels is a practically challenging problem in weakly-supervised
learning. The state-of-the-art approaches" Decoupling" and" Co-teaching+" claim that the" …

Provably consistent partial-label learning

L Feng, J Lv, B Han, M Xu, G Niu… - Advances in neural …, 2020 - proceedings.neurips.cc
Partial-label learning (PLL) is a multi-class classification problem, where each training
example is associated with a set of candidate labels. Even though many practical PLL …

Boosting deep learning risk prediction with generative adversarial networks for electronic health records

Z Che, Y Cheng, S Zhai, Z Sun… - 2017 IEEE International …, 2017 - ieeexplore.ieee.org
The rapid growth of Electronic Health Records (EHRs), as well as the accompanied
opportunities in Data-Driven Healthcare (DDH), has been attracting widespread interests …

Stacked autoencoders driven by semi-supervised learning for building extraction from near infrared remote sensing imagery

E Protopapadakis, A Doulamis, N Doulamis… - Remote Sensing, 2021 - mdpi.com
In this paper, we propose a Stack Auto-encoder (SAE)-Driven and Semi-Supervised (SSL)-
Based Deep Neural Network (DNN) to extract buildings from relatively low-cost satellite near …

Dynamic graph co-matching for unsupervised video-based person re-identification

M Ye, J Li, AJ Ma, L Zheng… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Cross-camera label estimation from a set of unlabeled training data is an extremely
important component in the unsupervised person re-identification (re-ID) systems. With the …

Enhance High Impedance Fault Detection and Location Accuracy via -PMUs

Q Cui, Y Weng - IEEE Transactions on Smart Grid, 2019 - ieeexplore.ieee.org
The high impedance fault (HIF) has random, irregular, and unsymmetrical characteristics,
making such a fault difficult to detect in distribution grids via conventional relay …

Learning from complementary labels

T Ishida, G Niu, W Hu… - Advances in neural …, 2017 - proceedings.neurips.cc
Collecting labeled data is costly and thus a critical bottleneck in real-world classification
tasks. To mitigate this problem, we propose a novel setting, namely learning from …

Learning with multiple complementary labels

L Feng, T Kaneko, B Han, G Niu, B An… - … on machine learning, 2020 - proceedings.mlr.press
A complementary label (CL) simply indicates an incorrect class of an example, but learning
with CLs results in multi-class classifiers that can predict the correct class. Unfortunately, the …

An information-theoretical approach to semi-supervised learning under covariate-shift

G Aminian, M Abroshan, MM Khalili… - International …, 2022 - proceedings.mlr.press
A common assumption in semi-supervised learning is that the labeled, unlabeled, and test
data are drawn from the same distribution. However, this assumption is not satisfied in many …

Semi-supervised classification based on classification from positive and unlabeled data

T Sakai, MC Plessis, G Niu… - … conference on machine …, 2017 - proceedings.mlr.press
Most of the semi-supervised classification methods developed so far use unlabeled data for
regularization purposes under particular distributional assumptions such as the cluster …