Next Article in Journal
Performance of the 5th Generation Indoor Wireless Technologies-Empirical Study
Next Article in Special Issue
Movement Analysis for Neurological and Musculoskeletal Disorders Using Graph Convolutional Neural Network
Previous Article in Journal
Data Science and Knowledge Discovery
Previous Article in Special Issue
Face Recognition Using Popular Deep Net Architectures: A Brief Comparative Study
Article

Fast Flow Reconstruction via Robust Invertible n × n Convolution

1
Computer Vision and Image Understanding Lab, Department of Computer Science and Computer Engineering, University of Arkansas, Fayetteville, AR 72501, USA
2
Department of Computer Science and Software Engineering, Concordia University, Montreal, QC H3G 2V4, Canada
3
Faculty of Information Technology, University of Science, VNU-HCM, Ho Chi Minh 721337, Vietnam
*
Author to whom correspondence should be addressed.
Academic Editor: Massimo Cafaro
Future Internet 2021, 13(7), 179; https://doi.org/10.3390/fi13070179
Received: 31 May 2021 / Revised: 29 June 2021 / Accepted: 6 July 2021 / Published: 8 July 2021
(This article belongs to the Collection Machine Learning Approaches for User Identity)
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. View Full-Text
Keywords: flow-based generative model; invertible n × n convolution; invertible and tractable transformations flow-based generative model; invertible n × n convolution; invertible and tractable transformations
Show Figures

Figure 1

MDPI and ACS Style

Truong, T.-D.; Duong, C.N.; Tran, M.-T.; Le, N.; Luu, K. Fast Flow Reconstruction via Robust Invertible n × n Convolution. Future Internet 2021, 13, 179. https://doi.org/10.3390/fi13070179

AMA Style

Truong T-D, Duong CN, Tran M-T, Le N, Luu K. Fast Flow Reconstruction via Robust Invertible n × n Convolution. Future Internet. 2021; 13(7):179. https://doi.org/10.3390/fi13070179

Chicago/Turabian Style

Truong, Thanh-Dat, Chi N. Duong, Minh-Triet Tran, Ngan Le, and Khoa Luu. 2021. "Fast Flow Reconstruction via Robust Invertible n × n Convolution" Future Internet 13, no. 7: 179. https://doi.org/10.3390/fi13070179

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop