activity
20222024
most citedA Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer

1 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2024

CALICO: Confident Active Learning with Integrated Calibration

Lorenzo S. Querol, Hajime Nagahara, Hideaki Hayashi

The growing use of deep learning in safety-critical applications, such as medical imaging, has raised concerns about limited labeled data, where this demand is amplified as model c…

cs.CV2024

Pseudo-label Learning with Calibrated Confidence Using an Energy-based Model

Masahito Toba, Seiichi Uchida, Hideaki Hayashi

In pseudo-labeling (PL), which is a type of semi-supervised learning, pseudo-labels are assigned based on the confidence scores provided by the classifier; therefore, accurate conf…

cs.CV20241 cited

Multi-Scale Spatio-Temporal Graph Convolutional Network for Facial Expression Spotting

Yicheng Deng, Hideaki Hayashi, Hajime Nagahara

Facial expression spotting is a significant but challenging task in facial expression analysis. The accuracy of expression spotting is affected not only by irrelevant facial moveme…

cs.LG20231 cited

A Hybrid of Generative and Discriminative Models Based on the Gaussian-coupled Softmax Layer

Hideaki Hayashi

Generative models have advantageous characteristics for classification tasks such as the availability of unsupervised data and calibrated confidence, whereas discriminative models…

cs.CV2022

Deep Bayesian Active-Learning-to-Rank for Endoscopic Image Data

Takeaki Kadota, Hideaki Hayashi, Ryoma Bise +2

Automatic image-based disease severity estimation generally uses discrete (i.e., quantized) severity labels. Annotating discrete labels is often difficult due to the images with am…