mlsanityData to 14 Oct 2026

Attention-guided Unified Network for Panoptic Segmentation

arXiv 1812.03904 ↗First posted 10 Dec 2018cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 19; 2022: 23; 2023: 17; 2024: 7; 2025: 4; 2026: 1.

71 papers.

Sort:

By area:

  1. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  2. 2023Personalize Segment Anything Model with One Shotcited by 250
  3. 2022Open-Vocabulary Universal Image Segmentation with MaskCLIPcited by 132
  4. 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
  5. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  6. 2022A Generalist Framework for Panoptic Segmentation of Images and Videoscited by 99
  7. 2021DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Camerascited by 67
  8. 2022CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentationcited by 60
  9. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 58
  10. 2021Part-aware Panoptic Segmentationcited by 56
  11. 2021Cross-View Regularization for Domain Adaptive Panoptic Segmentationcited by 41
  12. 2021Exemplar-Based Open-Set Panoptic Segmentation Networkcited by 38
38 more
  1. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  2. 2021PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentationcited by 36
  3. 2022TubeFormer-DeepLab: Video Mask Transformercited by 35
  4. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  5. 2023CLUSTSEG: Clustering for Universal Segmentationcited by 32
  6. 2021Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervisioncited by 31
  7. 2023Semantic Image Segmentation: Two Decades of Researchcited by 27
  8. 2023Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentationcited by 24
  9. 2021DeepLab2: A TensorFlow Library for Deep Labelingcited by 22
  10. 2024MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuningcited by 22
  11. 2023SANeRF-HQ: Segment Anything for NeRF in High Qualitycited by 20
  12. 2025PanSt3R: Multi-view Consistent Panoptic Segmentationcited by 20
  13. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  14. 2023DFormer: Diffusion-guided Transformer for Universal Image Segmentationcited by 19
  15. 2021Panoptic Segmentation: A Reviewcited by 18
  16. 2023ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentationcited by 18
  17. 2022Interactive Image Synthesis with Panoptic Layout Generationcited by 17
  18. 2022Uncertainty-aware Panoptic Segmentationcited by 17
  19. 2023PUPS: Point Cloud Unified Panoptic Segmentationcited by 16
  20. 2025Vision-Language Embodiment for Monocular Depth Estimationcited by 16
  21. 2022Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approachescited by 15
  22. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  23. 2022PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentationcited by 14
  24. 2022Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learningcited by 14
  25. 2022kMaX-DeepLab: k-means Mask Transformercited by 12
  26. 2021SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clusteringcited by 11
  27. 2022LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Networkcited by 11
  28. 2022SFNet: Faster and Accurate Semantic Segmentation via Semantic Flowcited by 10
  29. 2022Visual Recognition by Requestcited by 10
  30. 2022Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentationcited by 9
  31. 2022Dual Decision Improves Open-Set Panoptic Segmentationcited by 9
  32. 2022UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibrationcited by 8
  33. 2021Panoptic Segmentation Forecastingcited by 7
  34. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  35. 2023Dual Residual Attention Network for Image Denoisingcited by 6
  36. 2023Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learningcited by 6
  37. 2021Graphonomy: Universal Image Parsing via Graph Reasoning and Transfercited by 5
  38. 2021Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impairedcited by 5

50 most cited of 71 All 71 (JSON)