mlsanityData to 14 Oct 2026

Concentrate on Weakness: Mining Hard Prototypes for Few-Shot Medical Image Segmentation

arXiv 2505.21897 ↗First posted 28 May 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Few-Shot Medical Image Segmentation (FSMIS) has been widely used to train a model that can perform segmentation from only a few annotated images. However, most existing prototype-based FSMIS methods generate multiple prototypes from the support image solely by random sampling or local averaging, which can cause particularly severe boundary blurring due to the tendency for normal features accounting for the majority of features of a specific category. Consequently, we propose to focus more attention to those weaker features that are crucial for clear segmentation boundary. Specifically, we design a Support Self-Prediction (SSP) module to identify such weak features by comparing true support mask with one predicted by global support prototype. Then, a Hard Prototypes Generation (HPG) module is employed to generate multiple hard prototypes based on these weak features. Subsequently, a Multiple Similarity Maps Fusion (MSMF) module is devised to generate final segmenting mask in a dual-path fashion to mitigate the imbalance between foreground and background in medical images. Furthermore, we introduce a boundary loss to further constraint the edge of segmentation. Extensive experiments on three publicly available medical image datasets demonstrate that our method achieves state-of-the-art performance. Code is available at https://github.com/jcjiang99/CoW.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 27 of its 52 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

27 of 52 references.

References · 27

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,222
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2017Few-Shot Learning with Graph Neural Networkscited by 324
15 more
  1. 2020CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentationcited by 309
  2. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  3. 2016Multivariate mixture model for myocardium segmentation combining multi-source imagescited by 133
  4. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  5. 2017DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentationcited by 110
  6. 2020CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentationcited by 79
  7. 2020Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstractioncited by 70
  8. 2019'Squeeze & Excite' Guided Few-Shot Segmentation of Volumetric Imagescited by 69
  9. 2018HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentationcited by 66
  10. 2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
  11. 2021A Robust Volumetric Transformer for Accurate 3D Tumor Segmentationcited by 41
  12. 2023Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformercited by 28
  13. 2022Q-Net: Query-Informed Few-Shot Medical Image Segmentationcited by 24
  14. 2023Few Shot Medical Image Segmentation with Cross Attention Transformercited by 19
  15. 2024Few-Shot 3D Volumetric Segmentation with Multi-Surrogate Fusioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Focus on Background: Exploring SAM's Potential in Few-shot Medical Image Segmentation with Background-centric Promptingcited by 1
  2. 2026Attention-Based Prototype Calibration for Multi-Rater Few-Shot Medical Image Segmentationcited by 0
  3. 2026PSP: Harnessing Position and Shape Priors for Cross-Domain Few-Shot Medical Image Segmentationcited by 0