Biography
I am Shumpei Takezaki (竹崎 隼平 in Japanse), a Ph.D student at Kyushu University, Fukuoka, JAPAN, under the supervision of Prof. Seiichi Uhicda.
Before starting my Ph.D, I received my undergraduate degree in ECE from the Kagoshima Technical College, Kagoshima, JAPAN.
My research is on generative modeling. I am particularly interested in the applications of generative modeling for medical imaging.
News
- [Paper Acceptance]: Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels got accepted to WACV 2025 Oral.
- [Paper Acceptance]: Guidance-base Diffusion Models for Improving Photoacoustic Image Quality got accepted to BMVC 2024.
- [Paper Acceptance]: Cross-Domain Image Conversion by CycleDM got accepted to ICDAR 2024.
Recent Publications
For a more comprehensive list of publications, please see Publications or visit Google Scholar page.
Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels
Published in WACV 2025 [Paper] [Code]
Citation: Shumpei Takezaki, Kiyohito Tanaka, Seiichi Uchida, "Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels", WACV 2025
Guidance-base Diffusion Models for Improving Photoacoustic Image Quality
Published in BMVC 2024 [Paper]
Citation: Tatsuhiro Eguchi, Shumpei Takezaki, Mihoko Shimano, Takayuki Yagi, Ryoma Bise, "Guidance-base Diffusion Models for Improving Photoacoustic Image Quality", BMVC 2024
An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levels
Published in ISBI 2024 [Paper]
Citation: Shumpei Takezaki, Seiichi Uchida, "An Ordinal Diffusion Model for Generating Medical Images with Different Severity Levels", ISBI 2024
Contact
- Address: Human Interface Laboratory, Department of Advanced Information Technology, Kyushu University. 744, Motooka, Nishi-ku, Fukuoka-shi, 819-0395 JAPAN
- TEL: +81-92-802-3574
- E-mail: shumpei.takezaki[at]human.ait.kyushu-u.ac.jp