Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
复制标题
DOI：
--
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Haiyang Si;Zhiqiang Zhang;Feifan Lv;Gang Yu;Feng Lu
中科院分区：
文献类型：
--
作者：
Haiyang Si;Zhiqiang Zhang;Feifan Lv;Gang Yu;Feng Lu
实时语义分割在自动驾驶、机器人等行业应用中发挥着重要作用。这是一项具有挑战性的任务，因为需要同时考虑效率和性能。为了解决如此复杂的任务，本文提出了一种称为乘法空间融合网络（MSFNet）的高效 CNN，以实现快速准确的感知。所提出的MSFNet基于我们提出的多特征融合模块使用类边界监督来处理相关边界信息，可以获得空间信息并扩大感受野。因此，最终对1/8原始图像大小的特征图进行上采样可以在保持较高速度的同时取得令人印象深刻的结果。在 Cityscapes 和 Camvid 数据集上的实验表明，与现有方法相比，所提出的方法具有明显的优势。具体来说，它在 Cityscapes 测试数据集上以 41 FPS 的速度（1024*2048 输入）实现了 77.1% 的平均 IOU，在 Camvid 测试数据集上以 91 FPS 的速度实现了 75.4% 的平均 IOU。
Real-time semantic segmentation plays a significant role in industry applications, such as autonomous driving, robotics and so on. It is a challenging task as both efficiency and performance need to be considered simultaneously. To address such a complex task, this paper proposes an efficient CNN called Multiply Spatial Fusion Network (MSFNet) to achieve fast and accurate perception. The proposed MSFNet uses Class Boundary Supervision to process the relevant boundary information based on our proposed Multi-features Fusion Module which can obtain spatial information and enlarge receptive field. Therefore, the final upsampling of the feature maps of 1/8 original image size can achieve impressive results while maintaining a high speed. Experiments on Cityscapes and Camvid datasets show an obvious advantage of the proposed approach compared with the existing approaches. Specifically, it achieves 77.1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75.4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.