Search Results for author: Hiroshi Kaizuka

Found 2 papers, 0 papers with code

Gradient-based Data Augmentation for Semi-Supervised Learning

no code implementations28 Mar 2020 Hiroshi Kaizuka

It has been proved that the diversity of data used in CR is extremely important to obtain a model with high discrimination performance by CR.

Data Augmentation

ROI Regularization for Semi-supervised and Supervised Learning

no code implementations15 May 2019 Hiroshi Kaizuka, Yasuhiro Nagasaki, Ryo Sako

ROIreg focuses on the maximum probability of a posterior probability distribution g(x) obtained when inputting an unlabeled data sample x into a convolutional neural network (CNN).

Data Augmentation General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.