arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.01508cs.CVcs.AIcs.LG
收藏

EPVT:用于皮肤病变识别中领域泛化的环境感知提示视觉Transformer

EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition

Monash University(莫纳什大学);Inception Institute of AI(Inception人工智能研究院);Alfred Health(阿尔弗雷德医疗中心);The University of Queensland(昆士兰大学)

Siyuan Yan, Chi Liu, Zhen Yu, Lie Ju, Dwarikanath Mahapatrainst, Victoria Mar, Monika Janda, Peter Soyer, Zongyuan Ge

AI总结:

本文提出EPVT方法,通过在视觉Transformer中嵌入领域提示和共享提示,并引入领域提示生成器与领域混合策略,有效减少图像伪影依赖,显著提升皮肤病变识别在未见环境中的泛化能力。

摘要:

使用深度学习的皮肤病变识别取得了显著进展,在真实场景中部署这些系统的需求日益增加。然而,最近的研究表明,用于皮肤病变识别的深度神经网络可能过度依赖与疾病无关的图像伪影(即暗角、浓密毛发),导致在未见环境中的泛化能力较差。为了解决这个问题,我们提出了一种名为EPVT的新型领域泛化方法,该方法涉及将提示嵌入视觉Transformer中以协作学习来自不同领域的知识。具体而言,EPVT利用一组领域提示(每个领域提示充当领域专家)来捕获特定领域的知识;并利用一个共享提示来获取整个数据集的通用知识。为了促进知识共享和不同提示之间的交互,我们引入了一个领域提示生成器,该生成器能够在领域提示和共享提示之间实现低秩乘法更新。此外,还设计了一种领域混合策略来减少每个领域中同时出现的伪影,这允许更灵活的决策边界并缓解了错误分配领域标签的问题。在四个分布外数据集和六个不同的有偏ISIC数据集上的实验证明了EPVT在各种环境下皮肤病变识别中卓越的泛化能力。代码可在https://github.com/SiyuanYan1/EPVT获取。

英文摘要:

Skin lesion recognition using deep learning has made remarkable progress, and there is an increasing need for deploying these systems in real-world scenarios. However, recent research has revealed that deep neural networks for skin lesion recognition may overly depend on disease-irrelevant image artifacts (i.e., dark corners, dense hairs), leading to poor generalization in unseen environments. To address this issue, we propose a novel domain generalization method called EPVT, which involves embedding prompts into the vision transformer to collaboratively learn knowledge from diverse domains. Concretely, EPVT leverages a set of domain prompts, each of which plays as a domain expert, to capture domain-specific knowledge; and a shared prompt for general knowledge over the entire dataset. To facilitate knowledge sharing and the interaction of different prompts, we introduce a domain prompt generator that enables low-rank multiplicative updates between domain prompts and the shared prompt. A domain mixup strategy is additionally devised to reduce the co-occurring artifacts in each domain, which allows for more flexible decision margins and mitigates the issue of incorrectly assigned domain labels. Experiments on four out-of-distribution datasets and six different biased ISIC datasets demonstrate the superior generalization ability of EPVT in skin lesion recognition across various environments. Code is avaliable at https://github.com/SiyuanYan1/EPVT.

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。

↑