OPEN SET RECOGNITION BY REGULARISING CLASSIFIER WITH FAKE DATA GENERATED BY GENERATIVE ADVERSARIAL NETWORKS

被引:0
|
作者
Jo, Inhyuk [1 ]
Kim, Jungtaek [1 ]
Kang, Hyohyeong [2 ]
Kim, Yong-Deok [2 ]
Choi, Seungjin [1 ]
机构
[1] POSTECH, Dept Comp Sci & Engn, Pohang, South Korea
[2] Samsung Elect, Software R&D Ctr, Device Solut, Seoul, South Korea
来源
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年
关键词
Generative adversarial networks; Denoising autoencoder; Open set recognition; Feature matching;
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
We present a new method to generate fake data in unknown classes in generative adversarial networks (GANs) framework. The generator in GANs is trained to generate somewhat similar to data in known classes but the different one by modelling noisy distribution on feature space of a classifier using proposed marginal denoising autoencoder. The generated data are treated as fake instances in unknown classes and given to the classifier to make it be robust to the real unknown classes. Our results show that synthetic data can act as fake unknown classes and keep down the certainty of the classifier on real unknown classes meanwhile the classification capability of known classes is not degenerated, even improved.
引用
收藏
页码:2686 / 2690
页数:5
相关论文
共 50 条
  • [1] Improving the Performance of Open-Set Recognition with Generated Fake Data
    Halasz, Andras Pal
    Al Hemeary, Nawar
    Daubner, Lorant Szabolcs
    Zsedrovits, Tamas
    Tornai, Kalman
    ELECTRONICS, 2023, 12 (06)
  • [2] Open-set recognition of signal modulation based on generative adversarial networks
    Hao Y.
    Liu Z.
    Guo F.
    Zhang M.
    Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2019, 41 (11): : 2619 - 2624
  • [3] Adversarial compact wrapping classifier learning for open set recognition
    Zhang, Lin
    Wan, Minghua
    Huang, Pu
    Yang, Guowei
    INFORMATION SCIENCES, 2024, 680
  • [4] Addition of fake imagery generated by generative adversarial networks for improving crop classification
    Sonobe, Rei
    Tani, Hiroshi
    Shimamura, Hideki
    Mochizuki, Kan-ichiro
    ADVANCES IN SPACE RESEARCH, 2024, 74 (07) : 2901 - 2914
  • [5] Generative Adversarial Networks Classifier Optimized with Water Strider Algorithm for Fake Tweets Detection
    Muthulakshmi, V.
    Shajin, Francis H. H.
    Rose, J. Dhiviya
    Rajesh, P.
    IETE JOURNAL OF RESEARCH, 2024, 70 (02) : 1556 - 1571
  • [6] Data Augmentation for Voiceprint Recognition Using Generative Adversarial Networks
    Lin, Yao-San
    Chen, Hung-Yu
    Huang, Mei-Ling
    Hsieh, Tsung-Yu
    ALGORITHMS, 2024, 17 (12)
  • [7] Recognition Method of Pipeline Weld Defects Based on Auxiliary Classifier Generative Adversarial Networks
    Lang, Xianming
    IEEE Instrumentation and Measurement Magazine, 2022, 25 (02): : 69 - 77
  • [8] Recognition Method of Pipeline Weld Defects Based on Auxiliary Classifier Generative Adversarial Networks
    Lang, Xianming
    IEEE INSTRUMENTATION & MEASUREMENT MAGAZINE, 2022, 25 (02) : 69 - 77
  • [9] Auxiliary Conditional Generative Adversarial Networks for Image Data Set Augmentation
    Mudavathu, Kalpana Devi Bai
    Rao, V. P. Chandra Sekhara
    Ramana, K., V
    PROCEEDINGS OF THE 2018 3RD INTERNATIONAL CONFERENCE ON INVENTIVE COMPUTATION TECHNOLOGIES (ICICT 2018), 2018, : 263 - 269
  • [10] Detecting Fake Reviews with Generative Adversarial Networks for Mobile Social Networks
    Qu, Zheng
    Jia, Qingyao
    Lyu, Chen
    Liu, Jia
    Liu, Xiaoying
    Zheng, Kechen
    SECURITY AND COMMUNICATION NETWORKS, 2022, 2022