| Presentation | 2019-06-17 Triple GANs with adversarial disturbances for discriminative anomaly detection Hirotaka Hachiya, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Anomaly detection (AD) is an important machine learning task to detect outliers given only normal training data---applied to real-world problems such as surveillance camera. Recently, an advanced deep learning technique, generative adversarial nets (GANs) has been applied to AD, so that the generator is used to generate virtual anomalies and the discriminator is trained to classify instances into normal or (virtual) abnormal classes. However, existing GANs approach would have two problems:1) its performance is highly dependant on hyper parameters on early-stopping to build intentionally an imperfect generator,2) the detector tends to excessively focus on specific features, called "single mode" problem. In this study, to overcome these problems, we propose to introduce an additional discriminator to GANs, specifically for the AD, i.e., triple GANs, and then train it with virtual anomalies generated by the generator with latent adversarial disturbances. We show the effectiveness of our proposed method, called, "Triple GANomalies", through toy-data experiments using MNIST dataset. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | anomaly detectionGANsadversarial disturbanceCNN |
| Paper # | IBISML2019-4 |
| Date of Issue | 2019-06-10 (IBISML) |
| Conference Information | |
| Committee | NC / IBISML / IPSJ-MPS / IPSJ-BIO |
|---|---|
| Conference Date | 2019/6/17(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Okinawa Institute of Science and Technology |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Neurocomputing, Machine Learning Approach to Biodata Mining, and General |
| Chair | Hayaru Shouno(UEC) / Hisashi Kashima(Kyoto Univ.) / Masakazu Sekijima(Tokyo Tech) / Hiroyuki Kurata(Kyutech) |
| Vice Chair | Kazuyuki Samejima(Tamagawa Univ) / Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Kazuyuki Samejima(NAIST) / Masashi Sugiyama(NTT) / Koji Tsuda(Nagoya Inst. of Tech.) / (AIST) / (Nagoya Univ.) |
| Assistant | Takashi Shinozaki(NICT) / Ken Takiyama(TUAT) / Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / IPSJ Special Interest Group on Mathematical Modeling and Problem Solving / IPSJ Special Interest Group on Bioinformatics and Genomics |
|---|---|
| Language | ENG-JTITLE |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Triple GANs with adversarial disturbances for discriminative anomaly detection |
| Sub Title (in English) | |
| Keyword(1) | anomaly detectionGANsadversarial disturbanceCNN |
| 1st Author's Name | Hirotaka Hachiya |
| 1st Author's Affiliation | Wakayama University(Wakayama Univ.) |
| Date | 2019-06-17 |
| Paper # | IBISML2019-4 |
| Volume (vol) | vol.119 |
| Number (no) | IBISML-89 |
| Page | pp.pp.21-26(IBISML), |
| #Pages | 6 |
| Date of Issue | 2019-06-10 (IBISML) |