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 Nakamasa Inoue

Can Vision Transformers Learn without Natural Images?


Mar 24, 2021
Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto, Kenji Iwata, Nakamasa Inoue

* Project page: https://hirokatsukataoka16.github.io/Vision-Transformers-without-Natural-Images/ 

  Access Paper or Ask Questions

Pre-training without Natural Images


Jan 21, 2021
Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

* ACCV 2020 Best Paper Honorable Mention Award, Codes are publicly available: https://github.com/hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch 

  Access Paper or Ask Questions

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data


Jan 19, 2021
Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka

* Accepted to ICPR2020 

  Access Paper or Ask Questions

Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network


Apr 16, 2020
Tifani Warnita, Mariana Rodrigues Makiuchi, Nakamasa Inoue, Koichi Shinoda, Michitaka Yoshimura, Momoko Kitazawa, Kei Funaki, Yoko Eguchi, Taishiro Kishimoto


  Access Paper or Ask Questions

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation


Feb 29, 2020
Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue


  Access Paper or Ask Questions

Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition


Nov 12, 2018
Raden Mu'az Mun'im, Nakamasa Inoue, Koichi Shinoda


  Access Paper or Ask Questions

A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition


Aug 18, 2018
Thao Minh Le, Nakamasa Inoue, Koichi Shinoda

* Camera-ready manuscript for BMVC2018 

  Access Paper or Ask Questions

Few-Shot Adaptation for Multimedia Semantic Indexing


Jul 19, 2018
Nakamasa Inoue, Koichi Shinoda


  Access Paper or Ask Questions

I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification


Apr 01, 2018
Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda


  Access Paper or Ask Questions