Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Empirical Study on Optimizer Selection for Out-of-Distribution Generalization


Nov 18, 2022
Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas

* NeurIPS2022 Workshop on Distribution Shifts (DistShift) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Informative Sample-Aware Proxy for Deep Metric Learning


Nov 18, 2022
Aoyu Li, Ikuro Sato, Kohta Ishikawa, Rei Kawakami, Rio Yokota

* Accepted at ACM Multimedia Asia (MMAsia) 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Replacing Labeled Real-image Datasets with Auto-generated Contours


Jun 18, 2022
Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota

* Accepted to CVPR 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

OPIRL: Sample Efficient Off-Policy Inverse Reinforcement Learning via Distribution Matching


Sep 09, 2021
Hana Hoshino, Kei Ota, Asako Kanezaki, Rio Yokota

* Under submission 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation


Apr 01, 2021
Shun Iwase, Xingyu Liu, Rawal Khirodkar, Rio Yokota, Kris M. Kitani

* 8 pages, 5 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Epipolar-Guided Deep Object Matching for Scene Change Detection


Jul 30, 2020
Kento Doi, Ryuhei Hamaguchi, Shun Iwase, Rio Yokota, Yutaka Matsuo, Ken Sakurada

* 8 pages, 4 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Scalable and Practical Natural Gradient for Large-Scale Deep Learning


Feb 13, 2020
Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Chuan-Sheng Foo, Rio Yokota

* arXiv admin note: text overlap with arXiv:1811.12019 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Practical Deep Learning with Bayesian Principles


Jun 06, 2019
Kazuki Osawa, Siddharth Swaroop, Anirudh Jain, Runa Eschenhagen, Richard E. Turner, Rio Yokota, Mohammad Emtiyaz Khan

* Under review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Second-order Optimization Method for Large Mini-batch: Training ResNet-50 on ImageNet in 35 Epochs


Dec 05, 2018
Kazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, Satoshi Matsuoka

* 10 pages, 7 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email