所有中心距离最多几个token：基于领域不变提示微调的知识蒸馏
All Centers Are at most a Few Tokens Apart: Knowledge Distillation with Domain Invariant Prompt Tuning
AI总结：
本文提出领域不变提示微调（DIPT）方法，通过学习领域不变提示提升知识蒸馏效果，从而增强病理学领域模型的泛化能力。
摘要：
在计算病理学（CPath）中，领域泛化至关重要，因为临床中心之间由于染色协议、扫描仪设备和成像设置的差异而存在固有的领域偏移。视觉-语言模型（VLMs），如在多个领域上训练的病理学优化CLIP（PLIP），在知识蒸馏中起到重要作用。然而，由于对提示变化的敏感性，其预定义提示的零样本性能仍然有限。此外，与自然图像不同，病理学中心缺乏语义描述符（例如“草图”），使得为临床中心定义领域特定提示变得困难。这需要一种数据驱动的方法来学习领域特定的最终类别通用的连续提示。我们提出了领域不变提示微调（DIPT）用于知识蒸馏过程，这是一种新的步骤，为每个领域学习多个输入标记。这些标记分别针对每个领域进行训练，并在不同领域上进行平均，从而得到领域不变的提示。我们的学生模型通过利用DIPT学习的提示，从PLIP的文本编码器中蒸馏知识。这导致了视觉特征与领域不变嵌入的对齐，通过在多个领域上训练来增强泛化能力。我们的方法在领域泛化与病理学数据集的现有最先进（SOTA）知识蒸馏方法中显著提高了平均F1分数。这项工作有助于在异构数据源中部署稳健的CPath模型以解决现实世界中的临床问题。
英文摘要：
Domain generalization is critical in computational pathology (CPath) due to inherent domain shifts caused by variations in staining protocols, scanner devices, and imaging settings across clinical centers. Vision-language models (VLMs), such as PLIP-a pathology-tuned CLIP-trained on image-text pairs across diverse domains, serve as strong knowledge distillation sources. However, their zero-shot performance with predefined prompts remains limited due to sensitivity to prompt variations. Moreover, unlike natural images, histopathology centers lack semantic descriptors (e.g., 'sketch'), making it difficult to define domain-specific prompts for clinical centers. This requires a data-driven approach for learning domain-specific and ultimately class-generic continuous prompts. We propose Domain Invariant Prompt Tuning (DIPT) for knowledge distillation process, a novel step that learns multiple input tokens for each domain. These tokens are trained separately for each domain and are averaged across domains, leading to domain-invariant prompts. Our student model then distills knowledge from PLIP's text encoder by leveraging the prompts learned by DIPT. This leads to alignment of visual features with domain-invariant embeddings, enhancing generalization by training on multiple domains. Our method adds a significant improvement in average F1-score to existing state-of-the-art (SOTA) knowledge distillation approaches in domain generalization with histopathology datasets. This work helps the way of deploying robust CPath models in real-world clinical problems with heterogeneous data sources.
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。
