IDEAS home Printed from https://ideas.repec.org/a/gam/jftint/v13y2021i7p179-d590828.html
   My bibliography  Save this article

Fast Flow Reconstruction via Robust Invertible n × n Convolution

Author

Listed:
  • Thanh-Dat Truong

    (Computer Vision and Image Understanding Lab, Department of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR 72501, USA)

  • Chi Nhan Duong

    (Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 2V4, Canada)

  • Minh-Triet Tran

    (Faculty of Information Technology, University of Science, VNU-HCM, Ho Chi Minh 721337, Vietnam)

  • Ngan Le

    (Computer Vision and Image Understanding Lab, Department of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR 72501, USA)

  • Khoa Luu

    (Computer Vision and Image Understanding Lab, Department of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR 72501, USA)

Abstract

Flow-based generative models have recently become one of the most efficient approaches to model data generation. Indeed, they are constructed with a sequence of invertible and tractable transformations. Glow first introduced a simple type of generative flow using an invertible 1 × 1 convolution. However, the 1 × 1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible n × n convolution approach that overcomes the limitations of the invertible 1 × 1 convolution. In addition, our proposed network is not only tractable and invertible but also uses fewer parameters than standard convolutions. The experiments on CIFAR-10, ImageNet and Celeb-HQ datasets, have shown that our invertible n × n convolution helps to improve the performance of generative models significantly.

Suggested Citation

  • Thanh-Dat Truong & Chi Nhan Duong & Minh-Triet Tran & Ngan Le & Khoa Luu, 2021. "Fast Flow Reconstruction via Robust Invertible n × n Convolution," Future Internet, MDPI, vol. 13(7), pages 1-12, July.
    • Handle: RePEc:gam:jftint:v:13:y:2021:i:7:p:179-:d:590828
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1999-5903/13/7/179/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1999-5903/13/7/179/
    Download Restriction: no
    ---><---

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jftint:v:13:y:2021:i:7:p:179-:d:590828. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.