论文标题
通过自动深度，下采样联合决策和特征聚合的实时语义细分
Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
论文作者
论文摘要
为了满足实时语义分割领域中计算资源的严格要求，大多数方法都集中在轻度分割网络的手工设计上。最近，神经体系结构搜索（NAS）已被用来自动搜索网络的最佳构建块，但是网络深度，下采样策略和功能聚合方式仍然通过试用和错误提前设置。在本文中，我们提出了一个称为AutortNet的联合搜索框架，以自动化这些策略的设计。具体而言，我们提出了超细胞，以共同决定网络深度和下采样策略，以及一个聚集单元，以实现自动多尺度特征聚合。实验结果表明，AutortNet在CityScapes测试集上达到73.9％MIOU，并在NVIDIA TITANXP GPU卡上使用768x1536输入图像达到110.0 fps。
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.
