no code implementations • 4 Sep 2023 • Ryota Yoshihashi, Yuya Otsuka, Kenji Doi, Tomohiro Tanaka, Hirokatsu Kataoka
The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images.
no code implementations • 25 Nov 2022 • Ryota Yoshihashi, Shuhei Nishimura, Dai Yonebayashi, Yuya Otsuka, Tomohiro Tanaka, Takashi Miyazaki
Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training.
no code implementations • 10 Jun 2021 • Ryota Yoshihashi, Tomohiro Tanaka, Kenji Doi, Takumi Fujino, Naoaki Yamashita
In the deployment of scene-text spotting systems on mobile platforms, lightweight models with low computation are preferable.
no code implementations • 18 May 2021 • Ryota Yoshihashi, Rei Kawakami, ShaoDi You, Tu Tuan Trinh, Makoto Iida, Takeshi Naemura
Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable.
no code implementations • 18 Dec 2018 • Kenta Moriwaki, Ryota Yoshihashi, Rei Kawakami, ShaoDi You, Takeshi Naemura
It makes the reconstruction faithful to the input.
1 code implementation • CVPR 2019 • Ryota Yoshihashi, Wen Shao, Rei Kawakami, ShaoDi You, Makoto Iida, Takeshi Naemura
Existing open-set classifiers rely on deep networks trained in a supervised manner on known classes in the training set; this causes specialization of learned representations to known classes and makes it hard to distinguish unknowns from knowns.
no code implementations • 15 May 2018 • Seiichiro Fukuda, Ryota Yoshihashi, Rei Kawakami, ShaoDi You, Makoto Iida, Takeshi Naemura
We evaluated our proposed architecture on a combination of detection and segmentation using two datasets.
no code implementations • 14 Sep 2017 • Ryota Yoshihashi, Tu Tuan Trinh, Rei Kawakami, ShaoDi You, Makoto Iida, Takeshi Naemura
While generic object detection has achieved large improvements with rich feature hierarchies from deep nets, detecting small objects with poor visual cues remains challenging.