no code implementations • 19 Mar 2024 • Haruya Ishikawa, Takumi Iida, Yoshinori Konishi, Yoshimitsu Aoki
In this work, we address these challenges by leveraging the abundance of unlabeled data available.
no code implementations • 23 Aug 2023 • Sota Kato, Kazuhiro Hotta, Yuhki Hatakeyama, Yoshinori Konishi
Lite-HRNet Plus achieves two improvements: a novel fusion block based on a channel attention and a novel output module with less computational intensity using multi-resolution feature maps.
no code implementations • 26 Mar 2021 • Hiroki Sakuma, Yoshinori Konishi
Recently proposed DNN-based stereo matching methods that learn priors directly from data are known to suffer a drastic drop in accuracy in new environments.
no code implementations • 6 Oct 2020 • Yuhki Hatakeyama, Hiroki Sakuma, Yoshinori Konishi, Kohei Suenaga
Several techniques have been proposed to address this problem; one of which is RISE, which explains a classification result by a heatmap, called a saliency map, which explains the significance of each pixel.
2 code implementations • 5 Mar 2020 • Felix von Drigalski, Chisato Nakashima, Yoshiya Shibata, Yoshinori Konishi, Joshua C. Triyonoputro, Kaidi Nie, Damien Petit, Toshio Ueshiba, Ryuichi Takase, Yukiyasu Domae, Taku Yoshioka, Yoshihisa Ijiri, Ixchel G. Ramirez-Alpizar, Weiwei Wan, Kensuke Harada
We propose a versatile robotic system for kitting and assembly tasks which uses no jigs or commercial tool changers.
no code implementations • 21 Nov 2018 • Yoshinori Konishi, Kosuke Hattori, Manabu Hashimoto
BPT which is an efficient tree-based data structures for a large number of templates and template matching on rearranged feature maps where nearby features are linearly aligned accelerate the pose estimation.