mlsanityData to 7 Oct 2026

Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network

arXiv 2109.05353 ↗First posted 11 Sep 2021cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We present Border-SegGCN, a novel architecture to improve semantic segmentation by refining the border outline using graph convolutional networks (GCN). The semantic segmentation network such as Unet or DeepLabV3+ is used as a base network to have pre-segmented output. This output is converted into a graphical structure and fed into the GCN to improve the border pixel prediction of the pre-segmented output. We explored and studied the factors such as border thickness, number of edges for a node, and the number of features to be fed into the GCN by performing experiments. We demonstrate the effectiveness of the Border-SegGCN on the CamVid and Carla dataset, achieving a test set performance of 81.96% without any post-processing on CamVid dataset. It is higher than the reported state of the art mIoU achieved on CamVid dataset by 0.404%

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 62 references that are in the map. First posted on arXiv 11 Sep 2021.

Builds on

39 of 62 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  10. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  11. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  12. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
27 more
  1. 2018Link Prediction Based on Graph Neural Networkscited by 829
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  5. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  6. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  7. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  8. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  9. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  10. 2019An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognitioncited by 151
  11. 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
  12. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 122
  13. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  14. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 100
  15. 2017Geometric Matrix Completion with Recurrent Multi-Graph Neural Networkscited by 88
  16. 2017In-Place Activated BatchNorm for Memory-Optimized Training of DNNscited by 81
  17. 2018Fully Convolutional Adaptation Networks for Semantic Segmentationcited by 75
  18. 2015Efficient piecewise training of deep structured models for semantic segmentationcited by 71
  19. 2014Convolutional Feature Masking for Joint Object and Stuff Segmentationcited by 41
  20. 2018Memory Attention Networks for Skeleton-based Action Recognitioncited by 36
  21. 2017Situation Recognition with Graph Neural Networkscited by 34
  22. 2019A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenescited by 33
  23. 2016Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFscited by 27
  24. 2015Fully Connected Deep Structured Networkscited by 24
  25. 2014Feedforward semantic segmentation with zoom-out featurescited by 21
  26. 2020Res3ATN -- Deep 3D Residual Attention Network for Hand Gesture Recognition in Videoscited by 10
  27. 2018Image-Level Attentional Context Modeling Using Nested-Graph Neural Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022A Benchmark of Video-Based Clothes-Changing Person Re-Identificationcited by 4