# Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs

arXiv: https://arxiv.org/abs/2002.02117 · HTML: https://mlsanity.com/paper/2002.02117/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2020.

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

- [Abandoning the Bayer-Filter to See in the Dark](https://mlsanity.com/paper/2203.04042/) (2022)
- [Fake-image detection with Robust Hashing](https://mlsanity.com/paper/2102.01313/) (2021)
- [Spatiotemporal Multi-scale Bilateral Motion Network for Gait Recognition](https://mlsanity.com/paper/2209.12364/) (2022)
- [Localization of Ultra-dense Emitters with Neural Networks](https://mlsanity.com/paper/2305.05542/) (2023)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain](https://mlsanity.com/paper/2108.01892/) (2021)

## Abstract (arXiv)

In this paper, we propose a fixed convolutional layer with an order of smoothness not only for avoiding checkerboard artifacts in convolutional neural networks (CNNs) but also for enhancing the performance of CNNs, where the smoothness of its filter kernel can be controlled by a parameter. It is well-known that a number of CNNs generate checkerboard artifacts in both of two process: forward-propagation of upsampling layers and backward-propagation of strided convolutional layers. The proposed layer can perfectly prevent checkerboard artifacts caused by strided convolutional layers or upsampling layers including transposed convolutional layers. In an image-classification experiment with four CNNs: a simple CNN, VGG8, ResNet-18, and ResNet-101, applying the fixed layers to these CNNs is shown to improve the classification performance of all CNNs. In addition, the fixed layer are applied to generative adversarial networks (GANs), for the first time. From image-generation results, a smoother fixed convolutional layer is demonstrated to enable us to improve the quality of images generated with GANs.