Semantic Class Distribution Learning for Debiasing Semi-Supervised Medical Image Segmentation

• URL: http://arxiv.org/abs/2603.05202v1
• Date: Thu, 05 Mar 2026 14:13:53 GMT
• Title: Semantic Class Distribution Learning for Debiasing Semi-Supervised Medical Image Segmentation
• Authors: Yingxue Su, Yiheng Zhong, Keying Zhu, Zimu Zhang, Zhuoru Zhang, Yifang Wang, Yuxin Zhang, Jingxin Liu,
• Abstract summary: Class imbalance causes minority structures to be overwhelmed by dominant classes in feature representations.<n>We propose the Semantic Class Distribution Learning (SCDL) framework, a plug-and-play module that mitigates supervision and representation biases.<n> Experiments on the Synapse and AMOS datasets demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics.
• Score: 13.713097789787717
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical image segmentation is critical for computer-aided diagnosis. However, dense pixel-level annotation is time-consuming and expensive, and medical datasets often exhibit severe class imbalance. Such imbalance causes minority structures to be overwhelmed by dominant classes in feature representations, hindering the learning of discriminative features and making reliable segmentation particularly challenging. To address this, we propose the Semantic Class Distribution Learning (SCDL) framework, a plug-and-play module that mitigates supervision and representation biases by learning structured class-conditional feature distributions. SCDL integrates Class Distribution Bidirectional Alignment (CDBA) to align embeddings with learnable class proxies and leverages Semantic Anchor Constraints (SAC) to guide proxies using labeled data. Experiments on the Synapse and AMOS datasets demonstrate that SCDL significantly improves segmentation performance across both overall and class-level metrics, with particularly strong gains on minority classes, achieving state-of-the-art results. Our code is released at https://github.com/Zyh55555/SCDL.

Related papers

• Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation [0.2765106384328772]
  We propose a novel self-supervised contrastive learning framework for medical image segmentation, dubbed PolyCL.<n>PolyCL learns and transfers context-aware discriminant features useful for segmentation from an innovative surrogate.<n>We show that PolyCL outperforms fully-supervised and self-supervised baselines in both low-data and cross-domain scenarios.
  arXiv  Detail & Related papers  (2025-05-25T16:11:48Z)
• Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier Calibration [14.556686415877602]
  We propose a new Long-tailed Medical Diagnosis (LMD) framework for balanced medical image classification on long-tailed datasets.<n>Our framework significantly surpasses state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-02-05T14:57:23Z)
• SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation [53.010417880335424]
  Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos. Recent studies have shown the potential of contrastive learning in unsupervised representation learning using unlabelled data. We propose a novel Semantic-guided Multi-level Contrast scheme with a Neighbourhood-Consistency-Aware unit (SMC-NCA) to extract strong frame-wise representations.
  arXiv  Detail & Related papers  (2023-12-19T17:26:44Z)
• Combating Representation Learning Disparity with Geometric Harmonization [50.29859682439571]
  We propose a novel Geometric Harmonization (GH) method to encourage category-level uniformity in representation learning. Our proposal does not alter the setting of SSL and can be easily integrated into existing methods in a low-cost manner.
  arXiv  Detail & Related papers  (2023-10-26T17:41:11Z)
• Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation [14.536384387956527]
  We develop a novel Multi-Scale Cross Supervised Contrastive Learning framework to segment structures in medical images. Our approach contrasts multi-scale features based on ground-truth and cross-predicted labels, in order to extract robust feature representations. It outperforms state-of-the-art semi-supervised methods by more than 3.0% in Dice.
  arXiv  Detail & Related papers  (2023-06-25T16:55:32Z)
• Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation [30.06702813637713]
  We propose a novel Inherent Consistent Learning (ICL) method to learn robust semantic category representations. The proposed method can outperform the state-of-the-art, especially when the number of annotated data is extremely limited.
  arXiv  Detail & Related papers  (2023-03-24T17:38:03Z)
• PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training [52.895952593202054]
  We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation. PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state. Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
  arXiv  Detail & Related papers  (2022-07-24T07:45:47Z)
• Learning Debiased and Disentangled Representations for Semantic Segmentation [52.35766945827972]
  We propose a model-agnostic and training scheme for semantic segmentation. By randomly eliminating certain class information in each training iteration, we effectively reduce feature dependencies among classes. Models trained with our approach demonstrate strong results on multiple semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-31T16:15:09Z)
• Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations [1.5791732557395552]
  Leaking GAN is a GAN-based semi-supervised architecture for retina vessel semantic segmentation. Our key idea is to pollute the discriminator by leaking information from the generator. This leads to more moderate generations that benefit the training of GAN.
  arXiv  Detail & Related papers  (2021-10-22T18:25:08Z)
• Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data [123.03252888189546]
  We propose Vicinal Labels Under Uncertainty (VLUU) to bridge the methodological gaps in partially supervised learning (PSL) under data scarcity. Motivated by multi-task learning and vicinal risk minimization, VLUU transforms the partially supervised problem into a fully supervised problem by generating vicinal labels. Our research suggests a new research direction in label-efficient deep learning with partial supervision.
  arXiv  Detail & Related papers  (2020-11-28T16:31:00Z)
• A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision [62.4773770041279]
  We develop a semi-supervised learning framework based on a teacher-student fashion for organ and lesion segmentation. We show our model is robust to the quality of bounding box and achieves comparable performance compared with full-supervised learning methods.
  arXiv  Detail & Related papers  (2020-10-23T07:58:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.