# Rethinking Dilated Convolution for Real-time Semantic Segmentation

Source: [Rethinking Dilated Convolution for Real-time Semantic Segmentation](<https://www.sota2.com/research/paper/68fa714c1e209131cea508a3>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:35:54.659Z

Authors: Roland Gao

Published: 2021-11-18T22:08:21.000Z

## Abstract

The field-of-view is an important metric when designing a model for semantic segmentation. To obtain a large field-of-view, previous approaches generally choose to rapidly downsample the resolution, usually with average poolings or stride 2 convolutions. We take a different approach by using dilated convolutions with large dilation rates throughout the backbone, allowing the backbone to easily tune its field-of-view by adjusting its dilation rates, and show that it's competitive with existing approaches. To effectively use the dilated convolution, we show a simple upper bound on the dilation rate in order to not leave gaps in between the convolutional weights, and design an SE-ResNeXt inspired block structure that uses two parallel $3\\times 3$ convolutions with different dilation rates to preserve the local details. Manually tuning the dilation rates for every block can be difficult, so we also introduce a differentiable neural architecture search method that uses gradient descent to optimize the dilation rates. In addition, we propose a lightweight decoder that restores local information better than common alternatives. To demonstrate the effectiveness of our approach, our model RegSeg achieves competitive results on real-time Cityscapes and CamVid datasets. Using a T4 GPU with mixed precision, RegSeg achieves 78.3 mIOU on Cityscapes test set at $37$ FPS, and 80.9 mIOU on CamVid test set at $112$ FPS, both without ImageNet pretraining.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Semantic Segmentation on Cityscapes (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-test.md>): Semantic segmentation; Cityscapes (test); mIoU: 79.1.

- [Semantic Segmentation on CamVid (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-camvid-test.md>): Semantic segmentation; CamVid (test); mIoU: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2111.09957>)

[PDF](<https://arxiv.org/pdf/2111.09957.pdf>)