让医学图像分割自动选最合适的提示，提升跨域泛化能力
From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation
- 根据输入图像特征从可学习提示库中动态检索专用提示
- 在多个医学数据集上实现跨域泛化性能显著提升
- 无需修改主干网络，适配性强，适合临床部署
视觉提示已成为无需更新参数即可将预训练模型适应新领域的有效方法。然而，现有提示方法通常为每个领域优化单一提示并统一应用于所有输入，难以应对领域内与跨领域差异，这在医学领域尤为关键。为此，我们提出APEX——一种自适应提示提取框架，通过从可学习提示记忆中检索输入相关的提示。该记忆存储多样且具有领域区分性的提示表征，并利用傅里叶频谱提取的领域特征进行查询。为学习鲁棒且具区分性的领域特征，我们引入一种新型低频特征对比学习（LFC）框架，对同领域表示进行聚类，同时分离不同领域表示。在两个医学分割任务上的大量实验表明，APEX显著提升了在已见和未见领域中的泛化能力。此外，它可与任何现有主干网络配合使用，并持续提升性能，证实其作为医学领域即插即用提示方案的有效性。代码已公开于https://github.com/cetinkayaevren/apex/
原文摘要 · Abstract (English)
Visual prompting has emerged as a powerful method for adapting pre-trained models to new domains without updating model parameters. However, existing prompting methods typically optimize a single prompt per domain and apply it uniformly to all inputs, limiting their ability to generalize under intra and inter-domain variability, which is especially critical in the medical field. To address this, we propose APEX, an Adaptive Prompt EXtraction framework that retrieves input-specific prompts from a learnable prompt memory. The memory stores diverse, domain-discriminative prompt representations and is queried via domain features extracted from the Fourier spectrum. To learn robust and discriminative domain features, we introduce a novel Low-Frequency Feature Contrastive (LFC) learning framework that clusters representations from the same domain while separating those from different domains. Extensive experiments on two medical segmentation tasks demonstrate that APEX significantly improves generalization across both seen and unseen domains. Furthermore, it complements any existing backbones and consistently enhances performance, confirming its effectiveness as a plug-and-play prompting solution in medical fields. The code is available at https://github.com/cetinkayaevren/apex/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。