论文标题
实时语义细分的密集双路径网络
Dense Dual-Path Network for Real-time Semantic Segmentation
论文作者
论文摘要
语义分割以高计算成本和大量参数取得了显着的结果。但是，现实世界应用需要在嵌入式设备上有效推理速度。以前的大多数作品通过降低网络的深度，宽度和层能力来解决挑战，这导致性能差。在本文中，我们引入了一个新颖的密集双路径网络（DDPNET），以在资源约束下进行实时语义分割。我们设计了一个具有密度连接性的轻质和功能强大的骨干，以促进整个网络中的功能再利用，以及拟议的双路径模块（DPM），以充分汇总多尺度上下文。同时，使用高分辨率特征地图的跳过体系结构构建了一个简单有效的框架，以完善分割输出，并从功能地图中利用上下文信息来改进热图。提出的DDPNET在平衡准确性和速度方面显示出明显的优势。具体来说，在CityScapes测试数据集上，DDPNET以52.6 fps的价格达到75.3％MIOU，输入1024 x 2048分辨率在单个GTX 1080TI卡上。与其他最先进的方法相比，DDPNET以可比的速度和更少的参数实现了明显的更好的精度。
Semantic segmentation has achieved remarkable results with high computational cost and a large number of parameters. However, real-world applications require efficient inference speed on embedded devices. Most previous works address the challenge by reducing depth, width and layer capacity of network, which leads to poor performance. In this paper, we introduce a novel Dense Dual-Path Network (DDPNet) for real-time semantic segmentation under resource constraints. We design a light-weight and powerful backbone with dense connectivity to facilitate feature reuse throughout the whole network and the proposed Dual-Path module (DPM) to sufficiently aggregate multi-scale contexts. Meanwhile, a simple and effective framework is built with a skip architecture utilizing the high-resolution feature maps to refine the segmentation output and an upsampling module leveraging context information from the feature maps to refine the heatmaps. The proposed DDPNet shows an obvious advantage in balancing accuracy and speed. Specifically, on Cityscapes test dataset, DDPNet achieves 75.3% mIoU with 52.6 FPS for an input of 1024 X 2048 resolution on a single GTX 1080Ti card. Compared with other state-of-the-art methods, DDPNet achieves a significant better accuracy with a comparable speed and fewer parameters.
