mlsanityData to 14 Oct 2026

Learning to In-paint: Domain Adaptive Shape Completion for 3D Organ Segmentation

arXiv 2308.08775 ↗First posted 17 Aug 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We aim at incorporating explicit shape information into current 3D organ segmentation models. Different from previous works, we formulate shape learning as an in-painting task, which is named Masked Label Mask Modeling (MLM). Through MLM, learnable mask tokens are fed into transformer blocks to complete the label mask of organ. To transfer MLM shape knowledge to target, we further propose a novel shape-aware self-distillation with both in-painting reconstruction loss and pseudo loss. Extensive experiments on five public organ segmentation datasets show consistent improvements over prior arts with at least 1.2 points gain in the Dice score, demonstrating the effectiveness of our method in challenging unsupervised domain adaptation scenarios including: (1) In-domain organ segmentation; (2) Unseen domain segmentation and (3) Unseen organ segmentation. We hope this work will advance shape analysis and geometric learning in medical imaging.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

30 of 37 references.

References · 30

  1. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  4. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  5. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  6. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  7. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
  8. 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
  9. 2021The Medical Segmentation Decathloncited by 628
  10. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  11. 2022AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentationcited by 351
  12. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 308
18 more
  1. 2022Context Autoencoder for Self-Supervised Representation Learningcited by 297
  2. 2021CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentationcited by 227
  3. 2018Boundary loss for highly unbalanced segmentationcited by 190
  4. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  5. 2017Image to Image Translation for Domain Adaptationcited by 171
  6. 2020Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentationcited by 134
  7. 2016Unsupervised Cross-Domain Image Generationcited by 125
  8. 2019Reducing the Hausdorff Distance in Medical Image Segmentation with Convolutional Neural Networkscited by 116
  9. 2018Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learningcited by 51
  10. 2020Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentationcited by 48
  11. 2019Shape-Aware Organ Segmentation by Predicting Signed Distance Mapscited by 41
  12. 2021DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptationcited by 37
  13. 2021Deep Implicit Statistical Shape Models for 3D Medical Image Delineationcited by 26
  14. 2022ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentationcited by 26
  15. 2022PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentationcited by 16
  16. 2019An Alarm System For Segmentation Algorithm Based On Shape Modelcited by 8
  17. 2022Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentationcited by 6
  18. 2022Deep Active Latent Surfaces for Medical Geometriescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking
  2. 2024Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models
  3. 2025Toward Using Machine Learning as a Shape Quality Metric for Liver Point Cloud Generation
  4. 2026Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic Models
  5. 2026Leveraging a Statistical Shape Model for Efficient Generation of Annotated Training Data: A Case Study on Liver Landmarks Segmentation
  6. 2024SC-Diff: 3D Shape Completion with Latent Diffusion Models
  7. 2021MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets
  8. 2026RARF: Region-Aware Rectified Flows for 3D Brain MRI Inpainting