mlsanityData to 7 Oct 2026

SUNet: Scale-aware Unified Network for Panoptic Segmentation

arXiv 2209.02877 ↗First posted 7 Sep 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Panoptic segmentation combines the advantages of semantic and instance segmentation, which can provide both pixel-level and instance-level environmental perception information for intelligent vehicles. However, it is challenged with segmenting objects of various scales, especially on extremely large and small ones. In this work, we propose two lightweight modules to mitigate this problem. First, Pixel-relation Block is designed to model global context information for large-scale things, which is based on a query-independent formulation and brings small parameter increments. Then, Convectional Network is constructed to collect extra high-resolution information for small-scale stuff, supplying more appropriate semantic features for the downstream segmentation branches. Based on these two modules, we present an end-to-end Scale-aware Unified Network (SUNet), which is more adaptable to multi-scale objects. Extensive experiments on Cityscapes and COCO demonstrate the effectiveness of the proposed methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 44 references that are in the map. First posted on arXiv 7 Sep 2022.

Builds on

39 of 44 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2017Mask R-CNNcited by 7,259
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
27 more
  1. 2018Panoptic Segmentationcited by 796
  2. 2019Panoptic Feature Pyramid Networkscited by 644
  3. 2019Panoptic-DeepLabcited by 362
  4. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  5. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  6. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  7. 2017Relation Networks for Object Detectioncited by 305
  8. 2019UPSNet: A Unified Panoptic Segmentation Networkcited by 175
  9. 2019Seamless Scene Segmentationcited by 112
  10. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  11. 2020Fully Convolutional Networks for Panoptic Segmentationcited by 92
  12. 2018Attention-guided Unified Network for Panoptic Segmentationcited by 71
  13. 2019AdaptIS: Adaptive Instance Selection Networkcited by 64
  14. 2019An End-to-End Network for Panoptic Segmentationcited by 46
  15. 2018Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Camerascited by 42
  16. 2020Unifying Training and Inference for Panoptic Segmentationcited by 37
  17. 2019Real-Time Panoptic Segmentation from Dense Detectionscited by 31
  18. 2019Learning Instance Occlusion for Panoptic Segmentationcited by 30
  19. 2020Bidirectional Graph Reasoning Network for Panoptic Segmentationcited by 26
  20. 2020BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentationcited by 25
  21. 2019Fast Panoptic Segmentation Networkcited by 19
  22. 2020Pixel Consensus Voting for Panoptic Segmentationcited by 10
  23. 2020Improving Panoptic Segmentation at All Scalescited by 10
  24. 2021Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approachcited by 10
  25. 2020Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentationcited by 9
  26. 2019SpatialFlow: Bridging All Tasks for Panoptic Segmentationcited by 4
  27. 2021Hierarchical Lov'asz Embeddings for Proposal-free Panoptic Segmentationcited by 4

Built on by

Not cited yet.