# Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation

arXiv: https://arxiv.org/abs/2003.14226 · HTML: https://mlsanity.com/paper/2003.14226/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [Lightweight and Progressively-Scalable Networks for Semantic Segmentation](https://mlsanity.com/paper/2207.13600/) (2022)
- [Reusable Architecture Growth for Continual Stereo Matching](https://mlsanity.com/paper/2404.00360/) (2024)
- [Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search](https://mlsanity.com/paper/2302.08481/) (2023)

## Abstract (arXiv)

To satisfy the stringent requirements on computational resources in the field of real-time semantic segmentation, most approaches focus on the hand-crafted design of light-weight segmentation networks. Recently, Neural Architecture Search (NAS) has been used to search for the optimal building blocks of networks automatically, but the network depth, downsampling strategy, and feature aggregation way are still set in advance by trial and error. In this paper, we propose a joint search framework, called AutoRTNet, to automate the design of these strategies. Specifically, we propose hyper-cells to jointly decide the network depth and downsampling strategy, and an aggregation cell to achieve automatic multi-scale feature aggregation. Experimental results show that AutoRTNet achieves 73.9% mIoU on the Cityscapes test set and 110.0 FPS on an NVIDIA TitanXP GPU card with 768x1536 input images.