# Fast Flow Reconstruction via Robust Invertible nxn Convolution

arXiv: https://arxiv.org/abs/1905.10170 · HTML: https://mlsanity.com/paper/1905.10170/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2019.

## Built on by (most cited first, 6 of 6)

- [The Right to Talk: An Audio-Visual Transformer Approach](https://mlsanity.com/paper/2108.03256/) (2021)
- [BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation](https://mlsanity.com/paper/2108.03267/) (2021)
- [DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition](https://mlsanity.com/paper/2203.10233/) (2022)
- [OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation](https://mlsanity.com/paper/2205.10738/) (2022)
- [CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars](https://mlsanity.com/paper/2212.00621/) (2022)
- [CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation](https://mlsanity.com/paper/2304.07372/) (2023)

## Abstract (arXiv)

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.