Search Results for author: Kazuma Sasaki

Found 3 papers, 1 papers with code

RETHINKING SELF-DRIVING : MULTI -TASK KNOWLEDGE FOR BETTER GENERALIZATION AND ACCIDENT EXPLANATION ABILITY

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.

Rethinking Self-driving: Multi-task Knowledge for Better Generalization and Accident Explanation Ability

1 code implementation28 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.

Joint Gap Detection and Inpainting of Line Drawings

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.