Multi-stage context refinement network for semantic segmentation

Convolutional neural networks have been widely used in image semantic segmentation. However, con-tinuous downsampling operations in convolutional neural networks (such as pooling or convolution with step size) reduce the initial image resolution and lose the spatial details of the image, resulting in blurred image segmentation results. To alleviate this problem, in this paper we propose a multi-stage context refinement network (MCRNet) for semantic segmentation. Specifically, we first construct a Lowest -resolution Chain Context Aggregation (LCCA) module to encode rich semantic information. For obtaining more spatial detail information, we further build a High-resolution Context Attention Refinement (HCAR) module consisting of context feature extraction and context feature refinement. Finally, MCRNet fuses the context information generated by LCCA and HCAR for pixel prediction. Experimental results on three challenging semantic segmentation datasets, namely PASCAL VOC2012, ADE20K and Cityscapes, reveals that our proposed MCRNet is effective. (c) 2023 Elsevier B.V. All rights reserved.

Automated summary

In this paper, a multi-stage context refinement network (MCRNet) is proposed for semantic segmentation. By constructing the Lowest-resolution Chain Context Aggregation (LCCA) module and the High-resolution Context Attention Refinement (HCAR) module, MCRNet can encode rich semantic information while preserving spatial details, resulting in improved image segmentation performance.