Attention-guided Unified Network for Panoptic Segmentation

TL;DR

This paper introduces AUNet, a unified network for panoptic segmentation that leverages attention mechanisms from foreground objects to improve background understanding, achieving state-of-the-art results on MS-COCO and Cityscapes.

Contribution

The paper proposes a novel unified framework with dual attention sources for simultaneous foreground and background segmentation, revealing their complementary relationship.

Findings

Achieves 46.5% PQ on MS-COCO

Achieves 59.0% PQ on Cityscapes

Sets new state-of-the-art performance

Abstract

This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level. Existing methods mostly dealt with these two problems separately, but in this paper, we reveal the underlying relationship between them, in particular, FG objects provide complementary cues to assist BG understanding. Our approach, named the Attention-guided Unified Network (AUNet), is a unified framework with two branches for FG and BG segmentation simultaneously. Two sources of attentions are added to the BG branch, namely, RPN and FG segmentation mask to provide object-level and pixel-level attentions, respectively. Our approach is generalized to different backbones with consistent accuracy gain in both FG and BG segmentation, and also sets new state-of-the-arts both in the MS-COCO (46.5% PQ) and Cityscapes (59.0% PQ) benchmarks.