no code implementations • ICLR 2019 • Zhihao LI, Toshiyuki MOTOYOSHI, Kazuma Sasaki, Tetsuya OGATA, Shigeki SUGANO
Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of train- ing driving dataset is limited (2) Lack of accident explanation ability when driving models don’t work as expected.
1 code implementation • 28 Sep 2018 • Zhihao Li, Toshiyuki Motoyoshi, Kazuma Sasaki, Tetsuya OGATA, Shigeki SUGANO
Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of training driving dataset is limited (2) Lack of accident explanation ability when driving models don't work as expected.
no code implementations • CVPR 2017 • Kazuma Sasaki, Satoshi Iizuka, Edgar Simo-Serra, Hiroshi Ishikawa
We evaluate our method qualitatively on a diverse set of challenging line drawings and also provide quantitative results with a user study, where it significantly outperforms the state of the art.