SUNet: Scale-aware Unified Network for Panoptic Segmentation
This work addresses a domain-specific problem for intelligent vehicles by providing incremental improvements in panoptic segmentation for multi-scale objects.
The paper tackles the challenge of segmenting objects of various scales in panoptic segmentation by proposing two lightweight modules, Pixel-relation Block and Convectional Network, to improve performance on large and small objects, with experiments on Cityscapes and COCO datasets demonstrating effectiveness.
Panoptic segmentation combines the advantages of semantic and instance segmentation, which can provide both pixel-level and instance-level environmental perception information for intelligent vehicles. However, it is challenged with segmenting objects of various scales, especially on extremely large and small ones. In this work, we propose two lightweight modules to mitigate this problem. First, Pixel-relation Block is designed to model global context information for large-scale things, which is based on a query-independent formulation and brings small parameter increments. Then, Convectional Network is constructed to collect extra high-resolution information for small-scale stuff, supplying more appropriate semantic features for the downstream segmentation branches. Based on these two modules, we present an end-to-end Scale-aware Unified Network (SUNet), which is more adaptable to multi-scale objects. Extensive experiments on Cityscapes and COCO demonstrate the effectiveness of the proposed methods.