Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA, SIP, SP |
2019-03-14 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
Image Super-Resolution via Generative Adversarial Network Considering Objective Quality Hiroya Yamamoto, Daichi Kitahara, Akira Hirabayashi (Ritsumeikan Univ.) EA2018-115 SIP2018-121 SP2018-77 |
We propose a super-resolution method based on a conventional technique using the generative adversarial network (GAN). T... [more] |
EA2018-115 SIP2018-121 SP2018-77 pp.93-98 |
EA, SIP, SP |
2019-03-14 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
Diffuse noise reduction using adversarial denoising autoencoder Hikari Tanabe, Naohiro Tawara, Tetsunori Kobayashi (Waseda Univ.), Masaru Fujieda, Katagiri Kazuhiro, Takashi Yazu (OKI), Tetsuji Ogawa (Waseda Univ.) EA2018-125 SIP2018-131 SP2018-87 |
In this study, we attempted to remove diffuse noise by a model combining a prefilter and an adversarial denoising autoen... [more] |
EA2018-125 SIP2018-131 SP2018-87 pp.155-160 |
EMM |
2019-03-13 16:25 |
Okinawa |
TBD |
Improving the robusteness of neural networks to adversarial examples by reducing color depth of training inage data Shuntaro Miyazato, Toshihiko Yamasaki, Kiyoharu Aizawa (UTokyo) EMM2018-109 |
In this research, we propose a method to train a neural network that is robust to adversarial examples to image classifi... [more] |
EMM2018-109 pp.95-100 |
NC, MBE (Joint) |
2019-03-05 16:15 |
Tokyo |
University of Electro Communications |
Performance improvement of fNIRS-BCI using generative adversarial networks Tomoyuki Nagasawa (Nagaoka Univ. of Tech.), Takanori Sato (National Inst. of Tech., Akita Col.), Isao Nambu, Yasuhiro Wada (Nagaoka Univ. of Tech.) NC2018-72 |
Since a lengthy functional near-infrared spectroscopy (fNIRS) measurement is uncomfortable for the participant, the numb... [more] |
NC2018-72 pp.151-156 |
IN, NS (Joint) |
2019-03-04 09:00 |
Okinawa |
Okinawa Convention Center |
Intrusion Detection System using semi-supervised learning with Adversarial Autoencoder Kazuki Hara, Kohei Shiomoto (Tokyo City Univ.) NS2018-193 |
In recent years the importance of intrusion detection system(IDS) is increasing. In particular, a method using machine l... [more] |
NS2018-193 pp.1-6 |
PRMU |
2018-12-13 14:55 |
Miyagi |
|
Fast Distributional Smoothing for CTC-VAT and its Application to Text Line Recognition Ryohei Tanaka, Soichiro Ono, Akio Furuhata (Toshiba Digital Solutions) PRMU2018-80 |
Virtual Adversarial Training (VAT), which smooths posterior distribution by minimizing distributional distance of poster... [more] |
PRMU2018-80 pp.29-34 |
AI |
2018-12-07 15:55 |
Fukuoka |
|
Toyoaki Kuwahara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC) AI2018-30 |
The emotion estimation by speech makes it possible to estimate with higher precision with the development of deep learni... [more] |
AI2018-30 pp.25-29 |
IBISML |
2018-11-05 15:10 |
Hokkaido |
Hokkaido Citizens Activites Center (Kaderu 2.7) |
[Poster Presentation]
Kei Yonekawa, Hao Niu, Mori Kurokawa, Arei Kobayashi (KDDI Research) IBISML2018-103 |
(Advance abstract in Japanese is available) [more] |
IBISML2018-103 pp.435-440 |
SANE |
2018-10-12 13:30 |
Tokyo |
The University of Electro-Communications |
Automatic Target Recognition based on Generative Adversarial Networks for Synthetic Aperture Radar Images Yang-Lang Chang, Bo-Yao Chen, Chih-Yuan Chu, Sina Hadipour (NTUT), Hirokazu Kobayashi (OIT) SANE2018-51 |
Synthetic Aperture Radar (SAR) is an all day and all weather condition imaging technique which is widely used in nationa... [more] |
SANE2018-51 pp.41-44 |
SP |
2018-08-27 11:35 |
Kyoto |
Kyoto Univ. |
[Poster Presentation]
An Experimental Study on Transforming the Emotion in Speech using GAN Kenji Yasuda, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC) SP2018-26 |
In domain transfer task deep learning has made it possible to generate more natural and highly accurate output. Especial... [more] |
SP2018-26 pp.19-22 |
AI |
2018-07-02 10:50 |
Hokkaido |
|
Effect of Flactuation of Training Data on Prediction Performance Sachio Hirokawa, Koji Okamura (Kyushu Univ.) AI2018-3 |
By applying machine learning to the case of spam, a spam identification model can be created. On the other hand, the att... [more] |
AI2018-3 pp.11-14 |
CCS |
2018-03-26 10:00 |
Tokyo |
Tokyo Univ. of Sci. (Morito Memorial Hall) |
Suppression Method of Mode Collapse in Generative Adversarial Nets Shinya Hidai, Hidehiro Nakano, Arata Miyauchi (Tokyo City Univ.) CCS2017-33 |
Generative Adversarial Nets (GAN) is constituted by two neural networks, Generator and Discrminator. Generator creates d... [more] |
CCS2017-33 pp.1-6 |
IBISML |
2017-11-10 13:00 |
Tokyo |
Univ. of Tokyo |
Estimation of Training Data Distribution from Probabilistic Classifier using Generative Adversarial Networks Kosuke Kusano, Jun Sakuma (Univ. Tsukuba) IBISML2017-76 |
Suppose we have a deep classification model $f$ that is trained with private samples that should not be released, but we... [more] |
IBISML2017-76 pp.301-308 |
PRMU |
2017-10-12 15:10 |
Kumamoto |
|
[Tutorial Lecture]
Families of GANs Tomohiro Takahashi (ABEJA) PRMU2017-80 |
Generative Adversarial Networks(GANs) have recently gained popularity due to their ability to synthesize images which ar... [more] |
PRMU2017-80 pp.95-100 |
PRMU |
2017-10-13 11:10 |
Kumamoto |
|
PRMU2017-87 |
Generative Adversarial Nets (GANs) is a pair of neural networks which can learn data distribution and generate various d... [more] |
PRMU2017-87 pp.139-144 |
PRMU, IBISML, IPSJ-CVIM [detail] |
2017-09-15 15:50 |
Tokyo |
|
Face Image Generation System Using Attribute information with DCGANs Yurika Sagawa, Masafumi Hagiwara (Keio Univ.) PRMU2017-52 IBISML2017-24 |
In this paper, we propose an attribute added face image generation system using Deep Convolutional Generative Adversaria... [more] |
PRMU2017-52 IBISML2017-24 pp.107-112 |
SP |
2017-01-21 11:00 |
Tokyo |
The University of Tokyo |
[Poster Presentation]
Evaluation of DNN-Based Voice Conversion Deceiving Anti-spoofing Verification Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari (UT) SP2016-69 |
This paper proposes a novel training algorithm for high-quality Deep Neural Network (DNN)-based voice conversion. To imp... [more] |
SP2016-69 pp.29-34 |
IBISML |
2015-11-27 14:00 |
Ibaraki |
Epochal Tsukuba |
[Poster Presentation]
Regularization by local distributional smoothing Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, Ken Nakae, Shin Ishii (Kyoto Univ.) IBISML2015-87 |
Smoothness regularization is a popular method to decrease generalization error. We propose a novel regularization techni... [more] |
IBISML2015-87 pp.257-264 |