# Style-Aware Blending and Prototype-Based Cross-Contrast Consistency for Semi-Supervised Medical Image Segmentation

arXiv: https://arxiv.org/abs/2507.20729 · HTML: https://mlsanity.com/paper/2507.20729/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer](https://mlsanity.com/paper/2112.04894/) (2021)
- [Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2203.01324/) (2022)
- [Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2207.14191/) (2022)
- [AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.01818/) (2024)
- [Semi-Supervised Learning by Augmented Distribution Alignment](https://mlsanity.com/paper/1905.08171/) (2019)
- [Adaptive Bidirectional Displacement for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2405.00378/) (2024)
- [DHC: Dual-debiased Heterogeneous Co-training Framework for Class-imbalanced Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2307.11960/) (2023)
- [Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2311.17325/) (2023)
- [Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.16214/) (2023)
- [The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2407.11356/) (2024)
- [Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2306.14293/) (2023)

## Abstract (arXiv)

Weak-strong consistency learning strategies are widely employed in semi-supervised medical image segmentation to train models by leveraging limited labeled data and enforcing weak-to-strong consistency. However, existing methods primarily focus on designing and combining various perturbation schemes, overlooking the inherent potential and limitations within the framework itself. In this paper, we first identify two critical deficiencies: (1) separated training data streams, which lead to confirmation bias dominated by the labeled stream; and (2) incomplete utilization of supervisory information, which limits exploration of strong-to-weak consistency. To tackle these challenges, we propose a style-aware blending and prototype-based cross-contrast consistency learning framework. Specifically, inspired by the empirical observation that the distribution mismatch between labeled and unlabeled data can be characterized by statistical moments, we design a style-guided distribution blending module to break the independent training data streams. Meanwhile, considering the potential noise in strong pseudo-labels, we introduce a prototype-based cross-contrast strategy to encourage the model to learn informative supervisory signals from both weak-to-strong and strong-to-weak predictions, while mitigating the adverse effects of noise. Experimental results demonstrate the effectiveness and superiority of our framework across multiple medical segmentation benchmarks under various semi-supervised settings.