Atsuto Maki

Atsuto Maki is a Professor of Computer Science at KTH Royal Institute of Technology, affiliated with the School of Electrical Engineering and Computer Science and the Division of Robotics, Perception and Learning. He holds a PhD from KTH and an MEng from the University of Tokyo. Previously, he served as an associate professor at Kyoto University and worked in industry for over a decade at Toshiba Research Cambridge Lab and Toshiba Corporate R&D, focusing on computer vision systems like radar image analysis.

His research spans machine learning, deep learning, and computer vision, including motion/object recognition, clustering, subspace analysis, and representation learning. He teaches Machine Learning (DD2421) and co-chairs the Master’s Programme in Machine Learning. Maki has over 30 patents in image analysis and is a board member of the Swedish Society for Automated Image Analysis.

Recent projects include grants like 'SeDECI' (semi-supervised learning with imbalanced data) and collaborations with NII, RIKEN AIP, and the University of Tokyo. He actively organizes conferences (e.g., ECCV 2026) and workshops, and holds leadership roles in academic partnerships.

Key awards include the Niwa-Takayanagi Best Paper Prize (2018). His work emphasizes practical applications in manufacturing, medical imaging, and autonomous systems, reflected in papers on synthetic data for quality inspection, sonar beamforming, and deep learning regularization techniques.