Single-shot Path Integrated Panoptic Segmentation
This paper tackles the problem of inefficient multi-pathway panoptic segmentation for computer vision researchers, offering an incremental improvement in efficiency and accuracy.
This paper addresses panoptic segmentation, a task combining instance and semantic segmentation, by proposing a single-shot method. Their approach, SPINet, integrates execution flows to generate a unified 'Panoptic-Feature' and achieves high efficiency and accuracy on COCO and Cityscapes benchmarks.
Panoptic segmentation, which is a novel task of unifying instance segmentation and semantic segmentation, has attracted a lot of attention lately. However, most of the previous methods are composed of multiple pathways with each pathway specialized to a designated segmentation task. In this paper, we propose to resolve panoptic segmentation in single-shot by integrating the execution flows. With the integrated pathway, a unified feature map called Panoptic-Feature is generated, which includes the information of both things and stuffs. Panoptic-Feature becomes more sophisticated by auxiliary problems that guide to cluster pixels that belong to the same instance and differentiate between objects of different classes. A collection of convolutional filters, where each filter represents either a thing or stuff, is applied to Panoptic-Feature at once, materializing the single-shot panoptic segmentation. Taking the advantages of both top-down and bottom-up approaches, our method, named SPINet, enjoys high efficiency and accuracy on major panoptic segmentation benchmarks: COCO and Cityscapes.