mlsanityData to 7 Oct 2026

Automatic segmentation of meniscus based on MAE self-supervision and point-line weak supervision paradigm

arXiv 2205.03525 ↗First posted 7 May 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Medical image segmentation based on deep learning is often faced with the problems of insufficient datasets and long time-consuming labeling. In this paper, we introduce the self-supervised method MAE(Masked Autoencoders) into knee joint images to provide a good initial weight for the segmentation model and improve the adaptability of the model to small datasets. Secondly, we propose a weakly supervised paradigm for meniscus segmentation based on the combination of point and line to reduce the time of labeling. Based on the weak label ,we design a region growing algorithm to generate pseudo-label. Finally we train the segmentation network based on pseudo-labels with weight transfer from self-supervision. Sufficient experimental results show that our proposed method combining self-supervision and weak supervision can almost approach the performance of purely fully supervised models while greatly reducing the required labeling time and dataset size.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 45 references that are in the map. First posted on arXiv 7 May 2022.

Builds on

26 of 45 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  6. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  7. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,518
  8. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  9. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  10. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  12. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
14 more
  1. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  2. 2020UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentationcited by 331
  3. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  4. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  5. 2019ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed datacited by 260
  6. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  7. 2018On Regularized Losses for Weakly-supervised CNN Segmentationcited by 121
  8. 2018Normalized Cut Loss for Weakly-supervised CNN Segmentationcited by 112
  9. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 97
  10. 2018Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Featurescited by 81
  11. 2019Joint Learning of Saliency Detection and Weakly Supervised Semantic Segmentationcited by 57
  12. 2018Semi-Supervised Semantic Image Segmentation with Self-correcting Networkscited by 36
  13. 2016Bottom-Up Top-Down Cues for Weakly-Supervised Semantic Segmentationcited by 5
  14. 2018Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentationcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 1.

2 papers.

  1. 2023Medical supervised masked autoencoders: Crafting a better masking strategy and efficient fine-tuning schedule for medical image classificationcited by 2
  2. 2025ERANet: Edge Replacement Augmentation for Semi-Supervised Meniscus Segmentation with Prototype Consistency Alignment and Conditional Self-Trainingcited by 1