MSP : Refine Boundary Segmentation via Multiscale Superpixel
This work addresses boundary refinement in semantic segmentation for computer vision applications, presenting an incremental improvement as a plug-and-play module.
The authors tackled the problem of improving boundary quality in semantic segmentation by proposing a multiscale superpixel module (MSP) that refines edges through guided message passing, achieving enhanced performance on multiple datasets without adding parameters.
In this paper, we propose a simple but effective message passing method to improve the boundary quality for the semantic segmentation result. Inspired by the generated sharp edges of superpixel blocks, we employ superpixel to guide the information passing within feature map. Simultaneously, the sharp boundaries of the blocks also restrict the message passing scope. Specifically, we average features that the superpixel block covers within feature map, and add the result back to each feature vector. Further, to obtain sharper edges and farther spatial dependence, we develop a multiscale superpixel module (MSP) by a cascade of different scales superpixel blocks. Our method can be served as a plug-and-play module and easily inserted into any segmentation network without introducing new parameters. Extensive experiments are conducted on three strong baselines, namely PSPNet, DeeplabV3, and DeepLabV3+, and four challenging scene parsing datasets including ADE20K, Cityscapes, PASCAL VOC, and PASCAL Context. The experimental results verify its effectiveness and generalizability.