VQ-Seg：基於向量量化標記擾動的半監督醫學影像分割方法

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

January 15, 2026

作者: Sicheng Yang, Zhaohu Xing, Lei Zhu

cs.AI

摘要

基于特征扰动的一致性学习是半监督医学图像分割中广泛采用的策略。然而，现有扰动方法多依赖于dropout机制，需谨慎手动调整丢弃率这一敏感超参数，该参数不仅难以优化，还可能导致次优的正则化效果。为突破此局限，我们提出VQ-Seg方法：首次采用向量量化（VQ）技术离散化特征空间，并设计可控制的量化扰动模块（QPM）以取代dropout。QPM通过重排码本索引的空间位置实现对离散表征的扰动，从而达成高效可控的正则化。为缓解量化可能造成的信息损失，我们设计了双分支架构，使图像重建与分割任务共享量化后的特征空间。此外，引入后量化特征适配器（PFA）融合基础模型（FM）的指导信息，以补充量化过程中损失的高层语义特征。我们还构建了包含828例中央型肺癌标注CT扫描的大规模肺癌（LC）数据集。在LC数据集及多个公开基准上的实验表明，本方法性能优于现有最优方案。代码已开源：https://github.com/script-Yang/VQ-Seg。

English

Consistency learning with feature perturbation is a widely used strategy in semi-supervised medical image segmentation. However, many existing perturbation methods rely on dropout, and thus require a careful manual tuning of the dropout rate, which is a sensitive hyperparameter and often difficult to optimize and may lead to suboptimal regularization. To overcome this limitation, we propose VQ-Seg, the first approach to employ vector quantization (VQ) to discretize the feature space and introduce a novel and controllable Quantized Perturbation Module (QPM) that replaces dropout. Our QPM perturbs discrete representations by shuffling the spatial locations of codebook indices, enabling effective and controllable regularization. To mitigate potential information loss caused by quantization, we design a dual-branch architecture where the post-quantization feature space is shared by both image reconstruction and segmentation tasks. Moreover, we introduce a Post-VQ Feature Adapter (PFA) to incorporate guidance from a foundation model (FM), supplementing the high-level semantic information lost during quantization. Furthermore, we collect a large-scale Lung Cancer (LC) dataset comprising 828 CT scans annotated for central-type lung carcinoma. Extensive experiments on the LC dataset and other public benchmarks demonstrate the effectiveness of our method, which outperforms state-of-the-art approaches. Code available at: https://github.com/script-Yang/VQ-Seg.