Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
MIKA (3rd) |
2021-10-28 10:30 |
Okinawa |
(Primary: On-site, Secondary: Online) |
[Poster Presentation]
Examination of Majority Decision Method for Network Intrusion Detection System Using Deep Learning Koko Nishiura, Yuju Ogawa, Tomotaka Kimura, Jun Cheng (Doshisha Univ.) |
In recent years, the importance of NIDS (Network Intrusion Detection Systems), which detects unauthorized access, has be... [more] |
|
PRMU |
2021-10-09 09:30 |
Online |
Online |
Explaining Adversarial Examples by the Embedding Structure of Data Manifold Hajime Tasaki, Yuji Kaneko, Jinhui Chao (Chuo Univ.) PRMU2021-19 |
It is widely known that adversarial examples cause misclassification in classifiers using deep learning. Inspite of nume... [more] |
PRMU2021-19 pp.17-21 |
SIS, ITE-BCT |
2021-10-07 14:25 |
Online |
Online |
Block-wise Transformation with Secret Key for Adversary Robust Defence of SVM model Ryota Iijima, MaungMaung AprilPyone, Hitoshi Kiya (TMU) SIS2021-13 |
In this paper, we propose a method for implementing support vector machine (SVM) models that are robust against adversar... [more] |
SIS2021-13 pp.17-22 |
SIS, ITE-BCT |
2021-10-08 11:30 |
Online |
Online |
Analysis of Writing Style on Wood Slips of the Chinese Han period Using Deep Generative Model Chiang Meng Yuan, Soh Yoshida, Takao Fujita, Mitsuji Muneyasu (Kansai Univ.) SIS2021-20 |
In this paper, we develop a method to objectively analyze the calligraphic styles of wood slips excavated in Northwester... [more] |
SIS2021-20 pp.54-59 |
EMM, IT |
2021-05-21 13:10 |
Online |
Online |
A Study of Detecting Adversarial Examples Using Sensitivities to Multiple Auto Encoders Yuma Yamasaki, Minoru Kuribayashi, Nobuo Funabiki (Okayama Univ.), Huy Hong Nguyen, Isao Echizen (NII) IT2021-11 EMM2021-11 |
By removing the small perturbations involved in adversarial examples, the image classification result returns to the cor... [more] |
IT2021-11 EMM2021-11 pp.60-65 |
CCS |
2021-03-29 16:05 |
Online |
Online |
IMAS-GAN: Unsupervised Domain Translation without Cycle Consistency Masashi Okada, Hidehiro Nakano, Arata Miyauchi (Tokyo City Univ.) CCS2020-28 |
CycleGAN realizes the translation between domains without using pair data. However, the configuration of two GANs and th... [more] |
CCS2020-28 pp.42-47 |
MI |
2021-03-17 13:45 |
Online |
Online |
Medical Image Style Translation by Adversarial Training with Paired Inputs Kazuki Fujioka (Kobe Univ.), Takashi Matsubara (Osaka Univ.), Kuniaki Uehara (Osaka Gakuin Univ.) MI2020-96 |
Medical image diagnosis by artificial intelligence requires a large amount of data for learning. However, preparing such... [more] |
MI2020-96 pp.212-217 |
SIS |
2021-03-04 09:00 |
Online |
Online |
Optimization source-filtere based speech waveform generation using adversarial training Hayato Mitsui, Yosuke Sugiura, Nozomiko Yasui, Tetsuya Shimamura (Saitama Univ.) SIS2020-35 |
This research aims to improve the accuracy of the source-filter based speech waveform generation model using deep learni... [more] |
SIS2020-35 pp.1-4 |
IE, ITS, ITE-MMS, ITE-ME, ITE-AIT [detail] |
2021-02-19 14:15 |
Online |
Online |
[Special Talk]
A Note on Electron Microscope Image Generation from Mix Proportion via Conditional Style Generative Adversarial Network for Rubber Materials Rintaro Yanagi, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.) |
Estimating the properties of rubber materials from ingredients is necessary to accelerate rubber material development. I... [more] |
|
NLC |
2020-09-10 15:25 |
Online |
Online |
Unsupervised Domain Adaptation for Dialogue Sequence Labeling
-- Application to Contact Center Tasks -- Shota Orihashi, Naoki Makishima, Mana Ihori, Akihiko Takashima, Tomohiro Tanaka, Ryo Masumura (NTT) NLC2020-8 |
This paper presents an unsupervised domain adaptation for utterance-level sequence labeling of conversation in a contact... [more] |
NLC2020-8 pp.34-39 |
MI |
2020-09-03 14:25 |
Online |
Online |
Proposal of 3D Generative Adversarial Network for Improving Image Ouality of Cone-Beam CT Images Takumi Hase, Megumi Nakao (Kyoto Univ.), Keoho Imanishi (e-Growth Co., Ltd), Mitsuhiro Nakamura, Tetsuya Matsuda (Kyoto Univ.) MI2020-29 |
Artifacts and defects included in Cone-beam CT (CBCT) images have become an obstacle in radiation therapy and surgery su... [more] |
MI2020-29 pp.51-56 |
CCS |
2020-03-26 11:00 |
Tokyo |
Hosei Univ. Ichigaya Campus (Cancelled but technical report was issued) |
Generative Adversarial Networks Handling Multiple Distances between Probability Distributions Shinya Hidai, Hidehiro Nakano, Arata Miyauchi (Tokyo City Univ.) CCS2019-39 |
Generative Adversarial Networks (GAN) are trained by alternately training two networks. Discriminator estimates the dist... [more] |
CCS2019-39 pp.21-24 |
IBISML |
2020-03-11 15:10 |
Kyoto |
Kyoto University (Cancelled but technical report was issued) |
Fairness Causes Vulnerability to Adversarial Attacks Koki Wataoka, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) IBISML2019-48 |
When using machine learning models in society, it is essential to be ensure classifiers are fair to race and gender. In ... [more] |
IBISML2019-48 pp.101-105 |
SIS |
2020-03-06 15:00 |
Saitama |
Saitama Hall (Cancelled but technical report was issued) |
Adversarial Training using Self-Attention Architecture for Speech Enhancement Network Yosuke Sugiura, Shimamura Tetsuya (Saitama Univ.) SIS2019-59 |
In this paper, we propose a new adversarial training for improving performance of the speech enhancement network.
In th... [more] |
SIS2019-59 pp.125-129 |
NC, MBE (Joint) |
2020-03-05 09:30 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Improving Adversarial Robustness Based on Adversarial Training Consideration Ryota Komiyama, Motonobu Hattori (Univ. of Yamanashi) NC2019-90 |
Neural networks are used for various tasks because of their high performance.
However, it is known that even a high-per... [more] |
NC2019-90 pp.83-88 |
NC, MBE (Joint) |
2020-03-05 10:45 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
YuruGAN: Yuru-Charas Generated by Generative Adversarial Networks Yuki Hagiwara, Toshihisa Tanaka (TUAT) NC2019-93 |
Yuru-chara is a mascot character created by local governments and companies for the purpose of publicizing information o... [more] |
NC2019-93 pp.101-106 |
MI |
2020-01-30 13:25 |
Okinawa |
OKINAWAKEN SEINENKAIKAN |
Extracting and Visualization of Essential Features for Staining Translation of Pathological Images Ryoichi Koga, Noriaki Hashimoto, Tatsuya Yokota (NIT), Masato Nakaguro, Kei Kohno, Shigeo Nakamura (NUI), Ichiro Takeuchi, Hidekata Hontani (NIT) MI2019-116 |
In this manuscript, we propose a method for stain translation of pathology images. When one constructs a computer aided ... [more] |
MI2019-116 pp.215-218 |
EA |
2019-12-12 14:25 |
Fukuoka |
Kyushu Inst. Tech. |
Performance improvement of speech enhancement network by multitask learning including noise information Haruki Tanaka (NITTC), Yosuke Sugiura, Nozomiko Yasui, Tetsuya Shimamura (Saitama Univ.), Ryoichi Miyazaki (NITTC) EA2019-70 |
In the signal processing field, there is a growing interest in speech enhancement.Recently, a lot of speech enhancement ... [more] |
EA2019-70 pp.31-36 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 14:15 |
Okinawa |
Okinawa Institute of Science and Technology |
Triple GANs with adversarial disturbances for discriminative anomaly detection Hirotaka Hachiya (Wakayama Univ.) IBISML2019-4 |
Anomaly detection (AD) is an important machine learning task to detect outliers given only normal training data---applie... [more] |
IBISML2019-4 pp.21-26 |
PRMU, BioX |
2019-03-18 10:00 |
Tokyo |
|
A Generative Self-Ensemble Approach to Simulated+Unsupervised Learning Yu Mitsuzumi (Kyoto Univ.), Go Irie (NTT), Atsushi Nakazawa (Kyoto Univ.), Akisato Kimura (NTT) BioX2018-52 PRMU2018-156 |
The simulated and unsupervised (S+U) learning framework is an effective approach in computer vision since it solves vari... [more] |
BioX2018-52 PRMU2018-156 pp.137-142 |