# Inception Convolution with Efficient Dilation Search

arXiv: https://arxiv.org/abs/2012.13587 · HTML: https://mlsanity.com/paper/2012.13587/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [GLiT: Neural Architecture Search for Global and Local Image Transformer](https://mlsanity.com/paper/2107.02960/) (2021)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [SDWNet: A Straight Dilated Network with Wavelet Transformation for Image Deblurring](https://mlsanity.com/paper/2110.05803/) (2021)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [BN-NAS: Neural Architecture Search with Batch Normalization](https://mlsanity.com/paper/2108.07375/) (2021)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)
- [DPFNet: A Dual-branch Dilated Network with Phase-aware Fourier Convolution for Low-light Image Enhancement](https://mlsanity.com/paper/2209.07937/) (2022)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [Neural Architecture Adaptation for Object Detection by Searching Channel Dimensions and Mapping Pre-trained Parameters](https://mlsanity.com/paper/2206.08509/) (2022)

## Abstract (arXiv)

As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computational costs. To fully explore the potential of dilated convolution, we proposed a new type of dilated convolution (referred to as inception convolution), where the convolution operations have independent dilation patterns among different axes, channels and layers. To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed. Based on statistical optimization, the EDO method operates in a low-cost manner and is extremely fast when it is applied on large scale datasets. Empirical results validate that our method achieves consistent performance gains for image recognition, object detection, instance segmentation, human detection, and human pose estimation. For instance, by simply replacing the 3x3 standard convolution in the ResNet-50 backbone with inception convolution, we significantly improve the AP of Faster R-CNN from 36.4% to 39.2% on MS COCO.