# XSepConv: Extremely Separated Convolution

arXiv: https://arxiv.org/abs/2002.12046 · HTML: https://mlsanity.com/paper/2002.12046/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Convolutional Networks with Oriented 1D Kernels](https://mlsanity.com/paper/2309.15812/) (2023)
- [Improving Convolutional Neural Networks for Fault Diagnosis by Assimilating Global Features](https://mlsanity.com/paper/2210.01077/) (2022)

## Abstract (arXiv)

Depthwise convolution has gradually become an indispensable operation for modern efficient neural networks and larger kernel sizes (≥5) have been applied to it recently. In this paper, we propose a novel extremely separated convolutional block (XSepConv), which fuses spatially separable convolutions into depthwise convolution to further reduce both the computational cost and parameter size of large kernels. Furthermore, an extra 2×2 depthwise convolution coupled with improved symmetric padding strategy is employed to compensate for the side effect brought by spatially separable convolutions. XSepConv is designed to be an efficient alternative to vanilla depthwise convolution with large kernel sizes. To verify this, we use XSepConv for the state-of-the-art architecture MobileNetV3-Small and carry out extensive experiments on four highly competitive benchmark datasets (CIFAR-10, CIFAR-100, SVHN and Tiny-ImageNet) to demonstrate that XSepConv can indeed strike a better trade-off between accuracy and efficiency.