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

Autor:	Sun, Peng, Wu, Jiaxiang, Li, Songyuan, Lin, Peiwen, Huang, Junzhou, Li, Xi
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: submitted to IJCV
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2003.14226 Zobrazit plný text záznamu View this record from Arxiv