Explicitly Multi-Modal Benchmarks for Multi-Objective Optimization

no code implementations • 7 Oct 2021 • Ryosuke Ota, Reiya Hagiwara, Naoki Hamada, Likun Liu, Takahiro Yamamoto, Daisuke Sakurai

In multi-objective optimization, designing good benchmark problems is an important issue for improving solvers.

Benchmarking

Anatomical-Guided Attention Enhances Unsupervised PET Image Denoising Performance

no code implementations • 2 Sep 2021 • Yuya Onishi, Fumio Hashimoto, Kibo Ote, Hiroyuki Ohba, Ryosuke Ota, Etsuji Yoshikawa, Yasuomi Ouchi

Although supervised convolutional neural networks (CNNs) often outperform conventional alternatives for denoising positron emission tomography (PET) images, they require many low- and high-quality reference PET image pairs.

Decoder Image Denoising