Document Type
Article
Publication Date
5-2021
Keywords
flow-based generative model; invertible n x n convolution; invertible and tractable transformations
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 1x1 convolution. However, the 1x1 convolution suffers from limited flexibility compared to the standard convolutions. In this paper, we propose a novel invertible n x n convolution approach that overcomes the limitations of the invertible 1x1 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 x n convolution helps to improve the performance of generative models significantly.
Citation
Truong, T., Duong, C. N., Tran, M., Le, N., & Luu, K. (2021). Fast Flow Reconstruction via Robust Invertible n x n Convolution. Future Internet, 13 (7), 179. https://doi.org/10.3390/fi13070179
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
