The image shows the parallel modules with atrous convolution:
With DeepLab-v3+, the DeepLab-v3 model is extended by adding a simple, yet effective, decoder module to refine the segmentation results, especially along object boundaries. The depth-wise separable convolution is applied to both atrous spatial pyramid pooling and decoder modules, resulting in a faster and stronger encoder-decoder network for semantic segmentation. The architecture is shown in the following diagram: