Takuya Akiba | DeepAI

AI Chat

Featured Co-authors

Jun Zhu
239 publications
Alan Yuille
192 publications
Yao Zhao
119 publications
Xiaolin Hu
58 publications
Yinpeng Dong
55 publications
Samy Bengio
55 publications
Ian Goodfellow
50 publications
Cihang Xie
44 publications
Jianyu Wang
44 publications
Tianyu Pang
35 publications
Ming Liang
23 publications

∙ 10/25/2019

Team PFDet's Methods for Open Images Challenge 2019

We present the instance segmentation and the object detection method use...

0 Yusuke Niitani, et al. ∙

∙ 08/01/2019

Chainer: A Deep Learning Framework for Accelerating the Research Cycle

Software frameworks for neural networks play a key role in the developme...

0 Seiya Tokui, et al. ∙

∙ 07/25/2019

Optuna: A Next-generation Hyperparameter Optimization Framework

The purpose of this study is to introduce new design-criteria for next-g...

0 Takuya Akiba, et al. ∙

∙ 05/28/2019

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

Recomputation algorithms collectively refer to a family of methods that ...

0 Mitsuru Kusumoto, et al. ∙

∙ 11/27/2018

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

Efficient and reliable methods for training of object detectors are in h...

0 Yusuke Niitani, et al. ∙

∙ 09/04/2018

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

We present a large-scale object detection system by team PFDet. Our syst...

0 Takuya Akiba, et al. ∙

∙ 03/31/2018

Adversarial Attacks and Defences Competition

To accelerate research on adversarial examples and robustness of machine...

0 Alexey Kurakin, et al. ∙

∙ 02/16/2018

Variance-based Gradient Compression for Efficient Distributed Deep Learning

Due to the substantial computational cost, training state-of-the-art dee...

0 Yusuke Tsuzuku, et al. ∙

∙ 11/12/2017

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

We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be ...

0 Takuya Akiba, et al. ∙

∙ 10/31/2017

ChainerMN: Scalable Distributed Deep Learning Framework

One of the keys for deep learning to have made a breakthrough in various...

0 Takuya Akiba, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world