mlsanityData to 14 Oct 2026

ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image

arXiv 2607.24453 ↗First posted 27 Jul 2026cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning from minimal human supervision is a long-standing goal in medical image analysis, where dense expert annotations are costly. We study retinal vessel segmentation in an extreme semi-supervised setting with one annotated image and a pool of unlabeled images. We propose ESRVS, which selects a representative reference image for manual annotation and transfers vessel cues using target-domain-adapted DINOv3 features. ESRVS constructs a multi granular vessel prototype, combines prototype-similarity maps with a physics-inspired prior to generate initial pseudo-labels, and refines the transferred supervision through weighted pseudo-label training and adversarial refinement. Across eight public datasets, ESRVS achieves the best Dice and clDice on six datasets, and the best HD95 on all eight datasets among the compared semi-supervised methods, although those methods use 10 to 20% labeled data. With Mask2Former, ESRVS retains on average 93.7% of fully supervised Dice and 95.1% of fully supervised clDice. These results demonstrate the potential of foundation-model label propagation for highly label-efficient retinal vessel segmentation. Code is available at https://github.com/IAANNH/ESRVS.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 48 references that are in the map. First posted on arXiv 27 Jul 2026.

Builds on

21 of 48 references.

References · 21

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  7. 2025DINOv3cited by 1,414
  8. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  9. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 463
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
  12. 2020clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentationcited by 294
9 more
  1. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 251
  2. 2019CE-Net: Context Encoder Network for 2D Medical Image Segmentationcited by 220
  3. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  4. 2020Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistencycited by 102
  5. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 100
  6. 2024Learnable Prompting SAM-induced Knowledge Distillation for Semi-supervised Medical Image Segmentationcited by 23
  7. 2023From CNN to Transformer: A Review of Medical Image Segmentation Modelscited by 22
  8. 2020Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Imagescited by 8
  9. 2023An Uncertainty-Aware Pseudo-Label Selection Framework using Regularized Conformal Predictioncited by 1

Built on by

Not cited yet.