SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

Abstract

The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling overlaps. In this study, we aim to model overlap relations among instances and resolve them for panoptic segmentation. Inspired by scene graph representation, we formulate the overlapping problem as a simplified case, named scene overlap graph. We leverage each object's category, geometry and appearance features to perform relational embedding, and output a relation matrix that encodes overlap relations. In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances. The mask logits after removing overlaps are fed into per-pixel instance \verb|id| classification, which leverages the panoptic supervision to assist in the modeling of overlap relations. Besides, we generate an approximate ground truth of overlap relations as the weak supervision, to quantify the accuracy of overlap relations predicted by our method. Experiments on COCO and Cityscapes demonstrate that our method is able to accurately predict overlap relations, and outperform the state-of-the-art performance for panoptic segmentation. Our method also won the Innovation Award in COCO 2019 challenge.

To appear in AAAI 2020. Our method also won the Innovation Award in COCO 2019 challenge

References in corpus (11)

• Learning Deconvolution Network for Semantic Segmentation
• A simple neural network module for relational reasoning
• Deformable Convolutional Networks
• DeeperLab: Single-Shot Image Parser
• Expectation-Maximization Attention Networks for Semantic Segmentation
• Scene Graph Generation by Iterative Message Passing
• Learning to Fuse Things and Stuff
• Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network
• Panoptic Feature Pyramid Networks
• An End-to-End Network for Panoptic Segmentation
• Learning Instance Occlusion for Panoptic Segmentation

Cited by in corpus (2)

• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Ada-Segment: Automated Multi-loss Adaptation for Panoptic Segmentation