Robust VAEs via Generating Process of Noise Augmented Data

no code implementations • 26 Jul 2024 • Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki, Yuhui Zhang, Takumi Nakagawa, Hiroki Waida, Yuichiro Wada, Takafumi Kanamori

Advancing defensive mechanisms against adversarial attacks in generative models is a critical research topic in machine learning.

Investigating Self-Supervised Image Denoising with Denaturation

no code implementations • 2 May 2024 • Hiroki Waida, Kimihiro Yamazaki, Atsushi Tokuhisa, Mutsuyo Wada, Yuichiro Wada

To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments.

Image Denoising Self-Supervised Learning

Deep Mapper: Efficient Visualization of Plausible Conformational Pathways

no code implementations • 29 Feb 2024 • Ziyad Oulhaj, Yoshiyuki Ishii, Kento Ohga, Kimihiro Yamazaki, Mutsuyo Wada, Yuhei Umeda, Takashi Kato, Yuichiro Wada, Hiroaki Kurihara

In our numerical experiments, based on an isometric latent space built on the common 50S-ribosomal dataset, the resulting Mapper graph successfully includes all the well-recognized plausible pathways.

Drug Discovery Topological Data Analysis