# SqueezeNAS: Fast neural architecture search for faster semantic segmentation

arXiv: https://arxiv.org/abs/1908.01748 · HTML: https://mlsanity.com/paper/1908.01748/

## Key facts

- Cited by 31 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 5 Aug 2019.

## Built on by (most cited first, 30 of 31)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.15954/) (2021)
- [HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers](https://mlsanity.com/paper/2106.06560/) (2021)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [Generic Neural Architecture Search via Regression](https://mlsanity.com/paper/2108.01899/) (2021)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning](https://mlsanity.com/paper/2207.03677/) (2022)
- [T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging](https://mlsanity.com/paper/2111.07535/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [Learning Versatile Neural Architectures by Propagating Network Codes](https://mlsanity.com/paper/2103.13253/) (2021)
- [RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving](https://mlsanity.com/paper/2108.08019/) (2021)
- [On Efficient Real-Time Semantic Segmentation: A Survey](https://mlsanity.com/paper/2206.08605/) (2022)
- [SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction](https://mlsanity.com/paper/2109.08963/) (2021)
- [Bag of Tricks for Neural Architecture Search](https://mlsanity.com/paper/2107.03719/) (2021)
- [Real-Time Semantic Segmentation: A Brief Survey & Comparative Study in Remote Sensing](https://mlsanity.com/paper/2309.06047/) (2023)
- [MinUn: Accurate ML Inference on Microcontrollers](https://mlsanity.com/paper/2210.16556/) (2022)
- [Greedy Network Enlarging](https://mlsanity.com/paper/2108.00177/) (2021)
- [Dilated SpineNet for Semantic Segmentation](https://mlsanity.com/paper/2103.12270/) (2021)
- [ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models](https://mlsanity.com/paper/2105.03176/) (2021)
- [TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplification](https://mlsanity.com/paper/2408.01311/) (2024)
- [Growing an architecture for a neural network](https://mlsanity.com/paper/2108.02231/) (2021)
- [Diversified Dynamic Routing for Vision Tasks](https://mlsanity.com/paper/2209.13071/) (2022)
- [Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search](https://mlsanity.com/paper/2302.08481/) (2023)
- [FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation](https://mlsanity.com/paper/2303.16322/) (2023)
- [SSS3D: Fast Neural Architecture Search For Efficient Three-Dimensional Semantic Segmentation](https://mlsanity.com/paper/2304.11207/) (2023)
- [ICDARTS: Improving the Stability and Performance of Cyclic DARTS](https://mlsanity.com/paper/2309.00664/) (2023)
- [P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation](https://mlsanity.com/paper/2310.15025/) (2023)
- [Multi-objective Differentiable Neural Architecture Search](https://mlsanity.com/paper/2402.18213/) (2024)

## Abstract (arXiv)

For real time applications utilizing Deep Neural Networks (DNNs), it is critical that the models achieve high-accuracy on the target task and low-latency inference on the target computing platform. While Neural Architecture Search (NAS) has been effectively used to develop low-latency networks for image classification, there has been relatively little effort to use NAS to optimize DNN architectures for other vision tasks. In this work, we present what we believe to be the first proxyless hardware-aware search targeted for dense semantic segmentation. With this approach, we advance the state-of-the-art accuracy for latency-optimized networks on the Cityscapes semantic segmentation dataset. Our latency-optimized small SqueezeNAS network achieves 68.02% validation class mIOU with less than 35 ms inference times on the NVIDIA AGX Xavier. Our latency-optimized large SqueezeNAS network achieves 73.62% class mIOU with less than 100 ms inference times. We demonstrate that significant performance gains are possible by utilizing NAS to find networks optimized for both the specific task and inference hardware. We also present detailed analysis comparing our networks to recent state-of-the-art architectures.