SpatialFlow: Bridging All Tasks for Panoptic Segmentation

By Qiang Chen, Anda Cheng, Xiangyu He, Peisong Wang, Jian Cheng. 2019

33 citations recorded by the source corpus.

Object location is fundamental to panoptic segmentation as it is related to all things and stuff in the image scene. Knowing the locations of objects in the image provides clues for segmenting and helps the network better understand the scene. How to integrate object location in both thing and stuff segmentation is a crucial problem. In this article, we propose spatial information flows to achieve this objective. The flows can bridge all sub-tasks in panoptic segmentation by delivering the object’s spatial context from the box regression task to others. More importantly, we design four parallel sub-networks to get a preferable adaptation of object spatial information in sub-tasks. Upon the sub-networks and the flows, we present a location-aware and unified framework for panoptic segmentation, denoted as SpatialFlow. We perform a detailed ablation study on each component and conduct extensive experiments to prove the effectiveness of SpatialFlow. Furthermore, we achieve state-of-the-art results, which are 47.9 PQ and 62.5 PQ respectively on MS-COCO and Cityscapes panoptic benchmarks.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Accurate Post-training Network Quantization via Bit-Split and Stitching (2020, background): “…range of computer vision tasks, including image recognition (Krizhevsky et al., 2012; Simonyan & Zis-serman, 2014; Chatﬁeld et al., 2014; He et al., 2016), object detection (Girshick et al., 2014; Ren et al., 2015; Liu et al., 2016), segmentation (Long et al., 2015; Chen et al., 2019) and so on.”
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation (2020, unknown): “5 SpatialFlow [6] X 40.”
Scaling Wide Residual Networks for Panoptic Segmentation (2020, unknown): “7 SpatialFlow [9] DCN-101 [17] 3 47.”