mlsanityData to 14 Oct 2026

End-to-End Segmentation via Patch-wise Polygons Prediction

arXiv 2112.02535 ↗First posted 5 Dec 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The leading segmentation methods represent the output map as a pixel grid. We study an alternative representation in which the object edges are modeled, per image patch, as a polygon with k vertices that is coupled with per-patch label probabilities. The vertices are optimized by employing a differentiable neural renderer to create a raster image. The delineated region is then compared with the ground truth segmentation. Our method obtains multiple state-of-the-art results: 76.26% mIoU on the Cityscapes validation, 90.92% IoU on the Vaihingen building segmentation benchmark, 66.82% IoU for the MoNU microscopy dataset, and 90.91% for the bird benchmark CUB. Our code for training and reproducing these results is attached as supplementary.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 5 Dec 2021.

Builds on

29 of 41 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2016Pyramid Scene Parsing Networkcited by 2,479
  9. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  12. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
17 more
  1. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 554
  2. 2017Neural 3D Mesh Renderercited by 437
  3. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  4. 2021Medical Transformer: Gated Axial-Attention for Medical Image Segmentationcited by 320
  5. 2018Context Encoding for Semantic Segmentationcited by 290
  6. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  7. 2018Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++cited by 120
  8. 2019Fast Interactive Object Annotation with Curve-GCNcited by 95
  9. 2019PolyTransform: Deep Polygon Transformer for Instance Segmentationcited by 92
  10. 2019HarDNet: A Low Memory Traffic Networkcited by 76
  11. 2018Learning deep structured active contours end-to-endcited by 38
  12. 2020Hierarchical Recurrent Attention Networks for Structured Online Mapscited by 38
  13. 2019DARNet: Deep Active Ray Network for Building Segmentationcited by 30
  14. 2020End-to-End Trainable Deep Active Contour Models for Automated Image Segmentation: Delineating Buildings in Aerial Imagerycited by 16
  15. 2019End to End Trainable Active Contours via Differentiable Renderingcited by 15
  16. 2016Deep Active Contourscited by 9
  17. 2020Exploration of Optimized Semantic Segmentation Architectures for edge-Deployment on Dronescited by 2

Built on by

Not cited yet.