ProtoCLIP：基于原型对齐的潜在细化用于鲁棒零样本胸部X光分类
ProtoCLIP: Prototype-Aligned Latent Refinement for Robust Zero-Shot Chest X-Ray Classification
AI总结：
ProtoCLIP通过针对性数据筛选和锚点对齐优化，提升零样本胸部X光分类的鲁棒性，在VinDr-CXR数据集上提升AUC2-10个百分点，尤其在肺部气胸检测中达到0.94的SOTA性能。
摘要：
零样本视觉-语言模型（VLMs）在胸部X光分类中展现出潜力，但其性能常受限于标签共现偏差、长尾类别不平衡和域移时的迁移不稳定性。我们提出ProtoCLIP，一种针对CLIP风格VLMs的细化策略，通过定向数据筛选和蒸馏锚点对齐提升零样本判别能力。具体而言，我们构建了以病理为核心的训练子集，利用精心挑选的负样本减少共现偏差。我们还引入了保持表示的蒸馏目标，以稳定适应的同时维持语义结构并提升临床相关共现病理的判别能力。在未见数据集VinDr-CXR上评估，ProtoCLIP在多个发现上优于强大的CLIP基线，提升AUC2-10个百分点。对于肺部气胸，ProtoCLIP实现了SOTA的AUC 0.94。这些结果表明，通过锚点引导的细化、精心设计的监督和受控的适应，可以在不需大规模重训练的情况下缓解医学VLMs中的常见零样本迁移失败问题。
英文摘要：
Zero-shot vision-language models (VLMs) have shown promise for chest radiograph classification, but their performance is often limited by confounding label co-occurrence, long-tail class imbalance, and transfer instability under domain shift. We propose ProtoCLIP, a refinement strategy for CLIP-style VLMs that improves zero-shot discrimination through targeted data curation and distilled anchor alignment. Specifically, we construct pathology-focused training subsets with curated negative samples to reduce co-occurrence bias. We also introduce a representation-preserving distillation objective to stabilize adaptation while maintaining semantic structure and improving discrimination of clinically relevant co-occurring pathologies. Evaluated on an unseen dataset VinDr-CXR, ProtoCLIP improves AUC by 2-10 percentage points over a strong CLIP-based baseline across multiple findings. For pneumothorax specifically, ProtoCLIP achieves a state-of-the-art AUC of 0.94. These results demonstrate that anchor-guided refinement, coupled with curated supervision and controlled adaptation, can mitigate common zero-shot transfer failures in medical VLMs without requiring large-scale retraining.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
