SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

TL;DR

SOGNet introduces a novel scene overlap graph approach to model and resolve overlaps in panoptic segmentation, significantly improving accuracy and winning the COCO 2019 Innovation Award.

Contribution

The paper proposes a new scene overlap graph model that explicitly captures and resolves overlaps in panoptic segmentation, a problem often overlooked in prior work.

Findings

Outperforms state-of-the-art on COCO and Cityscapes datasets.

Accurately predicts overlap relations with weak supervision.

Wins the COCO 2019 Innovation Award.

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.