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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Takuya Akiba

Team PFDet's Methods for Open Images Challenge 2019


Oct 25, 2019
Yusuke Niitani, Toru Ogawa, Shuji Suzuki, Takuya Akiba, Tommi Kerola, Kohei Ozaki, Shotaro Sano


  Access Paper or Ask Questions

Chainer: A Deep Learning Framework for Accelerating the Research Cycle


Aug 01, 2019
Seiya Tokui, Ryosuke Okuta, Takuya Akiba, Yusuke Niitani, Toru Ogawa, Shunta Saito, Shuji Suzuki, Kota Uenishi, Brian Vogel, Hiroyuki Yamazaki Vincent

* Accepted for Applied Data Science Track in KDD'19 

  Access Paper or Ask Questions

Optuna: A Next-generation Hyperparameter Optimization Framework


Jul 25, 2019
Takuya Akiba, Shotaro Sano, Toshihiko Yanase, Takeru Ohta, Masanori Koyama

* 10 pages, Accepted at KDD 2019 Applied Data Science track 

  Access Paper or Ask Questions

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation


May 28, 2019
Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama


  Access Paper or Ask Questions

Sampling Techniques for Large-Scale Object Detection from Sparsely Annotated Objects


Nov 27, 2018
Yusuke Niitani, Takuya Akiba, Tommi Kerola, Toru Ogawa, Shotaro Sano, Shuji Suzuki


  Access Paper or Ask Questions

PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track


Sep 04, 2018
Takuya Akiba, Tommi Kerola, Yusuke Niitani, Toru Ogawa, Shotaro Sano, Shuji Suzuki

* Technical report for Open Images Challenge 2018 Object Detection Track 

  Access Paper or Ask Questions

Adversarial Attacks and Defences Competition


Mar 31, 2018
Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe

* 36 pages, 10 figures 

  Access Paper or Ask Questions

Variance-based Gradient Compression for Efficient Distributed Deep Learning


Feb 20, 2018
Yusuke Tsuzuku, Hiroto Imachi, Takuya Akiba

* ICLR 2018 Workshop 

  Access Paper or Ask Questions

Extremely Large Minibatch SGD: Training ResNet-50 on ImageNet in 15 Minutes


Nov 12, 2017
Takuya Akiba, Shuji Suzuki, Keisuke Fukuda

* NIPS'17 Workshop: Deep Learning at Supercomputer Scale 

  Access Paper or Ask Questions

ChainerMN: Scalable Distributed Deep Learning Framework


Oct 31, 2017
Takuya Akiba, Keisuke Fukuda, Shuji Suzuki


  Access Paper or Ask Questions