1 citations · 1 across the 1 of their papers we have counts for
2 papers
cs.LG2020
Gradient-based Data Augmentation for Semi-Supervised Learning
Hiroshi Kaizuka
In semi-supervised learning (SSL), a technique called consistency regularization (CR) achieves high performance. It has been proved that the diversity of data used in CR is extreme…
cs.CV2019★ 1 cited
ROI Regularization for Semi-supervised and Supervised Learning
Hiroshi Kaizuka, Yasuhiro Nagasaki, Ryo Sako
We propose ROI regularization (ROIreg) as a semi-supervised learning method for image classification. ROIreg focuses on the maximum probability of a posterior probability distribut…