Cascaded ASPP and Attention Mechanism-based Deeplabv3+ Semantic Segmentation Model

Abstract

Deeplabv3+ is a standard semantic segmentation model, which adds decoding structure to recover spatial information of the image and uses the Atrous Spatial Pyramid Pooling (ASPP) module to solve the multi-scale problem of the image. However, the Deeplabv3+ model has some drawbacks regarding restoring details. Therefore, we propose the CB_Deeplabv3+ model. In the encoding structure of the CB_Deeplabv3+ model, we use ASPP modules cascaded in parallel to extend the network structure and enable the model to capture richer context information by increasing the information interaction between channels. At the same time, CB_Deeplabv3+ introduced the Convolutional Block Attention Module(CBAM) to solve the long-distance dependence problem in the encoding-decoding structure. Experimental evaluation results on the Part_VOC dataset show that CB_Deeplabv3+ achieves excellent performance for semantic segmentation.