Publications

You can also find my articles on my Google Scholar profile.

Learning from Synthetic Data via Provenance-Based Input Gradient Guidance

Koshiro Nagano, Ryo Fujii, Ryo Hachiuma, Fumiaki Sato, Taiki Sekii, Hideo Saito

CVPR 2026, Acceptance Rate: 25.42%, h5-index: 450, 2026

We propose a training method that leverages provenance-based input gradient guidance to improve learning from synthetic data.

Koshiro Nagano, Fumiaki Sato, Ryo Hachiuma, Kazuki Tsutsukawa, Taiki Sekii

ICIP 2025, 2025

We propose a generalized few-shot object detection method that freezes the pretrained backbone network during fine-tuning.

Koshiro Nagano, Yoshiharu Mukouyama, Takashi Nishimura, Hiroyuki Fujioka, Kenji Watanabe, Takio Kurita, Akinori Hidaka

ISCIE SSS 2020, 2021

We propose a U-Net-based noise reduction method for SEM images trained with an SSIM loss function.