Attention-guided Unified Network for Panoptic Segmentation
arXiv:1812.03904
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.
CVPR 2019
References in corpus (12)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Dual Attention Network for Scene Segmentation
- Proposal-free Network for Instance-level Object Segmentation
- Learning a Discriminative Feature Network for Semantic Segmentation
- Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network
- Panoptic Feature Pyramid Networks
- An End-to-End Network for Panoptic Segmentation
- Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs
- LabelBank: Revisiting Global Perspectives for Semantic Segmentation
- UPSNet: A Unified Panoptic Segmentation Network
Cited by in corpus (6)
- FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks
- An End-to-End Network for Panoptic Segmentation
- UPSNet: A Unified Panoptic Segmentation Network
- SpatialFlow: Bridging All Tasks for Panoptic Segmentation
- Detecting Reflections by Combining Semantic and Instance Segmentation
- Motion Control on Bionic Eyes: A Comprehensive Review