mlsanityData to 7 Oct 2026

Dual skip connections in U-Net, ResUnet and U-Net3+ for remote extraction of buildings

arXiv 2303.09064 ↗First posted 16 Mar 2023cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Urban buildings are extracted from high-resolution Earth observation (EO) images using semantic segmentation networks like U-Net and its successors. Each re-iteration aims to improve performance by employing a denser skip connection mechanism that harnesses multi-scale features for accurate object mapping. However, denser connections increase network parameters and do not necessarily contribute to precise segmentation. In this paper, we develop three dual skip connection mechanisms for three networks (U-Net, ResUnet, and U-Net3+) to selectively deepen the essential feature maps for improved performance. The three mechanisms are evaluated on feature maps of different scales, producing nine new network configurations. They are evaluated against their original vanilla configurations on four building footprint datasets of different spatial resolutions, including a multi-resolution (0.3+0.6+1.2m) dataset that we develop for complex urban environments. The evaluation revealed that densifying the large- and small-scale features in U-Net and U-Net3+ produce up to 0.905 F1, more than TransUnet (0.903) and Swin-Unet (0.882) in our new dataset with up to 19x fewer parameters. The results conclude that selectively densifying feature maps and skip connections enhances network performance without a substantial increase in parameters. The findings and the new dataset will contribute to the computer vision domain and urban planning decision processes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 77 references that are in the map. First posted on arXiv 16 Mar 2023.

Builds on

38 of 77 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  11. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  12. 2017Non-local Neural Networkscited by 2,290
26 more
  1. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  2. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  3. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  4. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  5. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  6. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  7. 2020Image Segmentation Using Deep Learning: A Surveycited by 659
  8. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  9. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  10. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  11. 2017Road Extraction by Deep Residual U-Netcited by 333
  12. 2020UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentationcited by 331
  13. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 271
  14. 2021TransFuse: Fusing Transformers and CNNs for Medical Image Segmentationcited by 258
  15. 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 219
  16. 2021UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformercited by 197
  17. 2019MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentationcited by 195
  18. 2018Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentationcited by 180
  19. 2020U-Net and its variants for medical image segmentation: theory and applicationscited by 169
  20. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  21. 2017Dual Path Networkscited by 119
  22. 2020DC-UNet: Rethinking the U-Net Architecture with Dual Channel Efficient CNN for Medical Images Segmentationcited by 28
  23. 2017Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networkscited by 24
  24. 2020MACU-Net for Semantic Segmentation of Fine-Resolution Remotely Sensed Imagescited by 8
  25. 2018Building Extraction at Scale using Convolutional Neural Network: Mapping of the United Statescited by 7
  26. 2021Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT imagescited by 1

Built on by

Not cited yet.