SqueezeNAS: Fast neural architecture search for faster semantic segmentation

5 Aug 2019  ·  Albert Shaw, Daniel Hunter, Forrest Iandola, Sammy Sidhu ·

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.

PDF Abstract

Results from the Paper


Ranked #51 on Semantic Segmentation on Cityscapes val (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation Cityscapes test SqueezeNAS (LAT Small) Mean IoU (class) 66.8% # 82
Semantic Segmentation Cityscapes test SqueezeNAS (LAT Large) Mean IoU (class) 72.5% # 60
Semantic Segmentation Cityscapes val SqueezeNAS (LAT XLarge) mIoU 75.2% # 51
Semantic Segmentation Cityscapes val SqueezeNAS (LAT Small) mIoU 68.0% # 68
Semantic Segmentation Cityscapes val SqueezeNAS (LAT Large) mIoU 73.6% # 56

Methods