# CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications

arXiv: https://arxiv.org/abs/2104.14126 · HTML: https://mlsanity.com/paper/2104.14126/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://mlsanity.com/paper/1802.10062/) (2018)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentation](https://mlsanity.com/paper/1805.04574/) (2018)
- [ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation](https://mlsanity.com/paper/1803.06815/) (2018)
- [DSFD: Dual Shot Face Detector](https://mlsanity.com/paper/1810.10220/) (2018)
- [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://mlsanity.com/paper/1903.11816/) (2019)
- [SSH: Single Stage Headless Face Detector](https://mlsanity.com/paper/1708.03979/) (2017)
- [DetNet: A Backbone network for Object Detection](https://mlsanity.com/paper/1804.06215/) (2018)
- [Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery](https://mlsanity.com/paper/1709.00179/) (2017)
- [Smoothed Dilated Convolutions for Improved Dense Prediction](https://mlsanity.com/paper/1808.08931/) (2018)
- [Enhanced CNN for image denoising](https://mlsanity.com/paper/1810.11834/) (2018)
- [FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA](https://mlsanity.com/paper/2002.04971/) (2020)

## Abstract (arXiv)

The field of view (FOV) of convolutional neural networks is highly related to the accuracy of inference. Dilated convolutions are known as an effective solution to the problems which require large FOVs. However, for general-purpose hardware or dedicated hardware, it usually takes extra time to handle dilated convolutions compared with standard convolutions. In this paper, we propose a network module, Cascaded and Separable Structure of Dilated (CASSOD) Convolution, and a special hardware system to handle the CASSOD networks efficiently. A CASSOD-Net includes multiple cascaded 2 × 2 dilated filters, which can be used to replace the traditional 3 × 3 dilated filters without decreasing the accuracy of inference. Two example applications, face detection and image segmentation, are tested with dilated convolutions and the proposed CASSOD modules. The new network for face detection achieves higher accuracy than the previous work with only 47% of filter weights in the dilated convolution layers of the context module. Moreover, the proposed hardware system can accelerate the computations of dilated convolutions, and it is 2.78 times faster than traditional hardware systems when the filter size is 3 × 3.