mlsanityData to 7 Oct 2026

PolyTransform: Deep Polygon Transformer for Instance Segmentation

arXiv 1912.02801 ↗First posted 5 Dec 2019cs.CVcited by 92

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In particular, we first exploit a segmentation network to generate instance masks. We then convert the masks into a set of polygons that are then fed to a deforming network that transforms the polygons such that they better fit the object boundaries. Our experiments on the challenging Cityscapes dataset show that our PolyTransform significantly improves the performance of the backbone instance segmentation network and ranks 1st on the Cityscapes test-set leaderboard. We also show impressive gains in the interactive annotation setting. We release the code at https://github.com/uber-research/PolyTransform.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 22; 2023: 16; 2024: 14; 2025: 5; 2026: 3.

92 papers.

Sort:

By area:

  1. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 311
  2. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  3. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 243
  4. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  5. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 186
  6. 2023PolyFormer: Referring Image Segmentation as Sequential Polygon Generationcited by 147
  7. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  8. 2021Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understandingcited by 97
  9. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  10. 2022MiniViT: Compressing Vision Transformers with Weight Multiplexingcited by 88
  11. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  12. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
38 more
  1. 2021Mask Transfiner for High-Quality Instance Segmentationcited by 64
  2. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 57
  3. 2021Part-aware Panoptic Segmentationcited by 56
  4. 2024MGMap: Mask-Guided Learning for Online Vectorized HD Map Constructioncited by 52
  5. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  6. 2022Connecting the Dots: Floorplan Reconstruction Using Two-Level Queriescited by 48
  7. 2021RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Featurescited by 47
  8. 2021Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentationcited by 43
  9. 2021PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Imagescited by 42
  10. 2022RBGNet: Ray-based Grouping for 3D Object Detectioncited by 40
  11. 2022Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentationcited by 38
  12. 2021PlaneTR: Structure-Guided Transformers for 3D Plane Recoverycited by 33
  13. 2024TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learningcited by 29
  14. 2021Transformer Meets Convolution: A Bilateral Awareness Network for Semantic Segmentation of Very Fine Resolution Urban Scene Imagescited by 28
  15. 2023SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Processcited by 28
  16. 2022E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentationcited by 27
  17. 2022MGNet: Monocular Geometric Scene Understanding for Autonomous Drivingcited by 27
  18. 2022Towards General-Purpose Representation Learning of Polygonal Geometriescited by 21
  19. 2021Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistencycited by 19
  20. 2023PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentationcited by 19
  21. 2021Unknown Object Segmentation from Stereo Imagescited by 16
  22. 2023ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD Map Constructioncited by 16
  23. 2023Transformer as Linear Expansion of Learngenecited by 13
  24. 2021Adversarial Shape Learning for Building Extraction in VHR Remote Sensing Imagescited by 12
  25. 2021A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approachescited by 12
  26. 2021Infrared Small-Dim Target Detection with Transformer under Complex Backgroundscited by 12
  27. 2022SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentationcited by 12
  28. 2023BoxSnake: Polygonal Instance Segmentation with Box Supervisioncited by 12
  29. 2022Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answeringcited by 11
  30. 2022BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extractioncited by 11
  31. 2023EWT: Efficient Wavelet-Transformer for Single Image Denoisingcited by 11
  32. 2022RF-Next: Efficient Receptive Field Search for Convolutional Neural Networkscited by 10
  33. 2022Visual Recognition by Requestcited by 10
  34. 2023Recurrent Generic Contour-based Instance Segmentation with Progressive Learningcited by 9
  35. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  36. 2021VideoClick: Video Object Segmentation with a Single Clickcited by 8
  37. 2024PolyRoom: Room-aware Transformer for Floorplan Reconstructioncited by 8
  38. 2021INSTA-YOLO: Real-Time Instance Segmentationcited by 7

50 most cited of 92 All 92 (JSON)