arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.07979cs.CVeess.IV
收藏

一种新的双向无监督领域自适应分割框架

A New Bidirectional Unsupervised Domain Adaptation Segmentation Framework

Tencent Jarvis Lab(腾讯贾维斯实验室);National University of Defense Technology(国防科技大学)

Munan Ning, Cheng Bian, Dong Wei, Chenglang Yuan, Yaohua Wang, Yang Guo, Kai Ma, Yefeng Zheng

摘要:

域转移通常发生在跨域场景中,因为不同域之间存在很大的差距:当将一个在一个域中训练良好的深度学习模型应用到另一个目标域时,该模型通常表现不佳。为了解决这个问题,无监督领域自适应(UDA)技术被提出来弥合不同领域之间的差距,以提高模型的性能,在目标领域没有注释。特别是,UDA多模态医学图像分析,注释困难是一个实际问题有很大的价值。然而,大多数现有的UDA方法只能在一个自适应方向(例如,MRI到CT),但在另一种(CT到MRI)中通常表现不佳,限制了它们的实际使用。在本文中,我们提出了一个双向UDA(BiUDA)框架的基础上解开表示学习同样称职的双向UDA性能。该框架采用统一的域感知模式编码器,通过域控制器对不同域的图像进行自适应编码,并通过消除冗余参数提高模型效率。此外,为了避免在自适应过程中输入图像的内容和模式的失真,引入了内容模式一致性损失。此外,为了更好的UDA分割性能,提出了一种标签一致性策略,通过重组目标域样式的图像和相应的源域注释来提供额外的监督。在两个公共数据集上进行的比较实验和消融研究表明,我们的BiUDA框架优于当前最先进的UDA方法及其新颖设计的有效性。通过成功地解决双向适应,我们的BiUDA框架为现实世界的场景提供了灵活的UDA技术解决方案。

英文摘要:

Domain shift happens in cross-domain scenarios commonly because of the wide gaps between different domains: when applying a deep learning model well-trained in one domain to another target domain, the model usually performs poorly. To tackle this problem, unsupervised domain adaptation (UDA) techniques are proposed to bridge the gap between different domains, for the purpose of improving model performance without annotation in the target domain. Particularly, UDA has a great value for multimodal medical image analysis, where annotation difficulty is a practical concern. However, most existing UDA methods can only achieve satisfactory improvements in one adaptation direction (e.g., MRI to CT), but often perform poorly in the other (CT to MRI), limiting their practical usage. In this paper, we propose a bidirectional UDA (BiUDA) framework based on disentangled representation learning for equally competent two-way UDA performances. This framework employs a unified domain-aware pattern encoder which not only can adaptively encode images in different domains through a domain controller, but also improve model efficiency by eliminating redundant parameters. Furthermore, to avoid distortion of contents and patterns of input images during the adaptation process, a content-pattern consistency loss is introduced. Additionally, for better UDA segmentation performance, a label consistency strategy is proposed to provide extra supervision by recomposing target-domain-styled images and corresponding source-domain annotations. Comparison experiments and ablation studies conducted on two public datasets demonstrate the superiority of our BiUDA framework to current state-of-the-art UDA methods and the effectiveness of its novel designs. By successfully addressing two-way adaptations, our BiUDA framework offers a flexible solution of UDA techniques to the real-world scenario.

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。

↑