自监督视觉Transformer是可扩展的生成式模型，用于领域泛化
Self-supervised Vision Transformer are Scalable Generative Models for Domain Generalization
AI总结：
本文提出一种基于自监督Vision Transformer的生成式方法，通过合成多样组织病理学图像增强数据集，显著提升深度学习模型跨领域泛化能力，并在多个数据集上超越现有方法。
摘要：
尽管取得了显著进展，但将深度学习技术整合到具有影响力的临床应用（尤其是数字组织病理学领域）中，一直受到在不同成像领域和特征之间实现稳健泛化这一挑战的阻碍。该领域的传统缓解策略（如数据增强和染色颜色归一化）已被证明不足以解决这一局限，因此有必要探索替代方法。为此，我们提出了一种用于组织病理学图像领域泛化的新型生成式方法。我们的方法采用生成式、自监督的Vision Transformer来动态提取图像块的特性，并将其无缝注入原始图像，从而创建具有多样属性的新型合成图像。通过用这些合成图像丰富数据集，我们旨在增强其整体性，促进深度学习模型对未见领域的更好泛化。在两个不同的组织病理学数据集上进行的大量实验证明了我们所提方法的有效性，在Camelyon17-wilds挑战数据集（+2%）和第二个上皮-间质数据集（+26%）上大幅超越了当前最先进水平。此外，我们强调我们的方法能够随着越来越多可用的未标记数据样本以及更复杂、参数更多的架构而轻松扩展。源代码可在https://github.com/sdoerrich97/vits-are-generative-models获取。
英文摘要：
Despite notable advancements, the integration of deep learning (DL) techniques into impactful clinical applications, particularly in the realm of digital histopathology, has been hindered by challenges associated with achieving robust generalization across diverse imaging domains and characteristics. Traditional mitigation strategies in this field such as data augmentation and stain color normalization have proven insufficient in addressing this limitation, necessitating the exploration of alternative methodologies. To this end, we propose a novel generative method for domain generalization in histopathology images. Our method employs a generative, self-supervised Vision Transformer to dynamically extract characteristics of image patches and seamlessly infuse them into the original images, thereby creating novel, synthetic images with diverse attributes. By enriching the dataset with such synthesized images, we aim to enhance its holistic nature, facilitating improved generalization of DL models to unseen domains. Extensive experiments conducted on two distinct histopathology datasets demonstrate the effectiveness of our proposed approach, outperforming the state of the art substantially, on the Camelyon17-wilds challenge dataset (+2%) and on a second epithelium-stroma dataset (+26%). Furthermore, we emphasize our method's ability to readily scale with increasingly available unlabeled data samples and more complex, higher parametric architectures. Source code is available at https://github.com/sdoerrich97/vits-are-generative-models .
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。
