mlsanityData to 14 Oct 2026

Diversified Multi-prototype Representation for Semi-supervised Segmentation

arXiv 2111.08651 ↗First posted 16 Nov 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This work considers semi-supervised segmentation as a dense prediction problem based on prototype vector correlation and proposes a simple way to represent each segmentation class with multiple prototypes. To avoid degenerate solutions, two regularization strategies are applied on unlabeled images. The first one leverages mutual information maximization to ensure that all prototype vectors are considered by the network. The second explicitly enforces prototypes to be orthogonal by minimizing their cosine distance. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 16 Nov 2021.

Builds on

17 of 23 references.

References · 17

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  4. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  5. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  6. 2014Deep metric learning using Triplet networkcited by 422
  7. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  8. 2020Semi-supervised Medical Image Segmentation through Dual-task Consistencycited by 216
  9. 2020Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Imagescited by 152
  10. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  11. 2019Semi-Supervised Medical Image Segmentation via Learning Consistency under Transformationscited by 71
  12. 2019Deep Co-Training for Semi-Supervised Image Segmentationcited by 58
5 more
  1. 2021Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labelscited by 32
  2. 2018Deep semi-supervised segmentation with weight-averaged consistency targetscited by 21
  3. 2020Self-paced and self-consistent co-training for semi-supervised image segmentationcited by 18
  4. 2021Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularizationcited by 14
  5. 2021Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentationcited by 8

Built on by

Not cited yet.