论文标题
Sunet：庞大分割的比例意见统一网络
SUNet: Scale-aware Unified Network for Panoptic Segmentation
论文作者
论文摘要
Pastic分割结合了语义和实例细分的优势，可以为智能车辆提供像素级和实例级别的环境感知信息。但是，它挑战各种尺度的对象，尤其是在极小和小的物体上。在这项工作中，我们提出了两个轻量级模块来减轻此问题。首先，像素连接块旨在为大规模事物建模全局上下文信息，该信息基于与查询无关的公式建模，并带来了小参数增量。然后，构建对流网络以收集针对小规模内容的额外高分辨率信息，为下游分割分支提供更合适的语义特征。基于这两个模块，我们提出了一个端到端刻度量表统一网络（Sunet），该网络更适合多尺度对象。对城市景观和可可的广泛实验证明了所提出的方法的有效性。
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.
