结合ASPP与改进HRNet的多尺度图像语义分割方法研究

Multi-scale image semantic segmentation based on ASPP and improved HRNet

针对经典语义分割算法中存在的模型庞大、训练困难以及多尺度目标分割等问题,基于空洞空间金字塔池化(ASPP)和高分辨率网络(HRNet)提出了一种高效的多尺度图像语义分割方法。首先利用深度可分离卷积结合1*1卷积的方式改进了HRNet的基础模块,减少了模型参数;其次通过在全部的卷积层之后、修正线性单元(relu)激活函数之前添加批归一化层(BN)改善DeadRelu问题;最后添加了使用混合扩张卷积框架重构的ASPP,使用并行的上采样通道融合二者的优势,获得空间精准的分割结果,提出了Re-ASPP-HRNet。在公开数据集PASCAL VOC2012和CityScapes上的实验表明,改进后的方法相比于原HRNet分别实现了0.8%、0.5%平均交并比的精度提升,且减少了1/2的参数数量以及1/3占用内存。进一步提升了网络的性能,实现了更加高效可靠、有普适性的多尺度语义分割算法。

Aiming at the problems of huge model and multi-scale object segmentation in the classical semantic segmentation algorithm,an efficient multi-scale image semantic segmentation method based on ASPP and HRNet is proposed.Firstly,the basic block is improved by using deep separable convolution combined with 1*1 convolution to reduce the model parameters.Secondly,a batch normalization layer(BN)is added after all convolution layers and before the relu activation function to improve the dead relu problem.Finally,the improved ASPP module based on the hybrid dilated convolution is added,and the advantages of the two are fused by using the parallel upsampling channels to obtain the spatial accurate segmentation results.The RE-ASPP-HRNet is proposed.Results on Pascal voc2012 and CityScapes show that the proposed method is effective.Compared with the original HRNet,it can improve the accuracy of 0.8%or 0.5%MIoU,and reduce the number of parameters by 1/2 and memory by 1/3.We implement a more efficient and reliable multi-scale semantic segmentation algorithm.