Papers › Attention-guided Unified Network for Panoptic Segmentation

Attention-guided Unified Network for Panoptic Segmentation

10 Dec 2018CVPR 2019 6arXiv:1812.03904archive 2025-07-28

Yanwei Li, Xinze Chen, Zheng Zhu, Lingxi Xie, Guan Huang, Dalong Du, Xingang Wang

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Panoptic SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO test-dev AUNet (ResNext-152-FPN) PQ 46.5 #25 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNext-152-FPN) PQst 32.5 #25 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNext-152-FPN) PQth 55.8 #25 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-152-FPN) PQ 45.5 #26 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-152-FPN) PQst 31.6 #26 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-152-FPN) PQth 54.7 #26 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-101-FPN) PQ 45.2 #27 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-101-FPN) PQst 31.3 #27 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev AUNet (ResNet-101-FPN) PQth 54.4 #27 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes val AUNet (ResNet-101-FPN) AP 34.4 #30 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val AUNet (ResNet-101-FPN) PQ 59.0 #30 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val AUNet (ResNet-101-FPN) PQst 62.1 #30 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val AUNet (ResNet-101-FPN) PQth 54.8 #30 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val AUNet (ResNet-101-FPN) mIoU 75.6 #30 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingRPNReLUResNeXtResNeXt BlockResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections