mlsanityData to 14 Oct 2026

The Importance of Skip Connections in Biomedical Image Segmentation

arXiv 1608.04117 ↗First posted 14 Aug 2016cs.CVcited by 126

Not on the map. Why?

Abstract (arXiv)

In this paper, we study the influence of both long and short skip connections on Fully Convolutional Networks (FCN) for biomedical image segmentation. In standard FCNs, only long skip connections are used to skip features from the contracting path to the expanding path in order to recover spatial information lost during downsampling. We extend FCNs by adding short skip connections, that are similar to the ones introduced in residual networks, in order to build very deep FCNs (of hundreds of layers). A review of the gradient flow confirms that for a very deep FCN it is beneficial to have both long and short skip connections. Finally, we show that a very deep FCN can achieve near-to-state-of-the-art results on the EM dataset without any further post-processing.

Key facts. Cited by 126 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Aug 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 31; 2022: 31; 2023: 25; 2024: 18; 2025: 18; 2026: 3.

126 papers.

Sort:

By area:

  1. 2021UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformercited by 197
  2. 2022Medical Image Segmentation Review: The success of U-Netcited by 191
  3. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  4. 2023STU-Net: Scalable and Transferable Medical Image Segmentation Models Empowered by Large-Scale Supervised Pre-trainingcited by 100
  5. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
  6. 2023SA-Med2D-20M Dataset: Segment Anything in 2D Medical Imaging with 20 Million maskscited by 55
  7. 2021MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentationcited by 53
  8. 2021The Federated Tumor Segmentation (FeTS) Challengecited by 50
  9. 2022D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentationcited by 35
  10. 2021Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficientcited by 26
  11. 2022Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysiscited by 25
  12. 2023Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teachercited by 21
38 more
  1. 2021Calibrating the Dice loss to handle neural network overconfidence for biomedical image segmentationcited by 17
  2. 2024U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Modelscited by 17
  3. 2022CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoisingcited by 16
  4. 2023DA-TransUNet: Integrating Spatial and Channel Dual Attention with Transformer U-Net for Medical Image Segmentationcited by 16
  5. 2021Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentationcited by 12
  6. 2021T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imagingcited by 11
  7. 2022R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentationcited by 11
  8. 2024Quantum Denoising Diffusion Modelscited by 11
  9. 2023An investigation into the impact of deep learning model choice on sex and race bias in cardiac MR segmentationcited by 8
  10. 2025MediSee: Reasoning-based Pixel-level Perception in Medical Imagescited by 8
  11. 2021Cutting-edge 3D Medical Image Segmentation Methods in 2020: Are Happy Families All Alike?cited by 7
  12. 2022k-strip: A novel segmentation algorithm in k-space for the application of skull strippingcited by 7
  13. 2021Physics-based Differentiable Depth Sensor Simulationcited by 6
  14. 2021Continuous-Time Deep Glioma Growth Modelscited by 6
  15. 2022On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dicecited by 6
  16. 2022Segmentation in large-scale cellular electron microscopy with deep learning: A literature surveycited by 6
  17. 2022PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Cloudscited by 6
  18. 2022Theoretical analysis and experimental validation of volume bias of soft Dice optimized segmentation maps in the context of inherent uncertaintycited by 6
  19. 2023Sketch-based Medical Image Retrievalcited by 6
  20. 2021Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Datacited by 5
  21. 2022The Dice loss in the context of missing or empty labels: Introducing Phi and εcited by 5
  22. 2022Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directionscited by 5
  23. 2022BriFiSeg: a deep learning-based method for semantic and instance segmentation of nuclei in brightfield imagescited by 5
  24. 2022Visual-tactile Fusion for Transparent Object Grasping in Complex Backgroundscited by 5
  25. 2023PhysRFANet: Physics-Guided Neural Network for Real-Time Prediction of Thermal Effect During Radiofrequency Ablation Treatmentcited by 5
  26. 2024A gradient-based approach to fast and accurate head motion compensation in cone-beam CTcited by 5
  27. 2024Generalizable Single-Source Cross-modality Medical Image Segmentation via Invariant Causal Mechanismscited by 5
  28. 2021MixSearch: Searching for Domain Generalized Medical Image Segmentation Architecturescited by 4
  29. 2021Decomposing Normal and Abnormal Features of Medical Images into Discrete Latent Codes for Content-Based Image Retrievalcited by 4
  30. 2021MAG-Net: Multi-task attention guided network for brain tumor segmentation and classificationcited by 4
  31. 2021A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Imagescited by 4
  32. 2023SUD2: Supervision by Denoising Diffusion Models for Image Reconstructioncited by 4
  33. 2023DLSIA: Deep Learning for Scientific Image Analysiscited by 4
  34. 2024CAMS: Convolution and Attention-Free Mamba-based Cardiac Image Segmentationcited by 4
  35. 2025SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-trainingcited by 4
  36. 2021Analyzing Epistemic and Aleatoric Uncertainty for Drusen Segmentation in Optical Coherence Tomography Imagescited by 3
  37. 2023A Deep Active Contour Model for Delineating Glacier Calving Frontscited by 3
  38. 2023Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-trainingcited by 3

50 most cited of 126 All 126 (JSON)