论文标题
可以转移的内容：内窥镜病变细分的无监督域适应
What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation
论文作者
论文摘要
无监督的领域适应引起了人们对语义细分的越来越多的研究。但是，1）由于不同数据集之间相同病变的不同外观，大多数现有模型不能直接应用于医疗图像的病变转移； 2）已将同等的关注引起了所有语义表示，而不是忽略无关的知识，从而导致不可转移知识的负面转移。 To address these challenges, we develop a new unsupervised semantic transfer model including two complementary modules (i.e., T_D and T_F ) for endoscopic lesions segmentation, which can alternatively determine where and how to explore transferable domain-invariant knowledge between labeled source lesions dataset (e.g., gastroscope) and unlabeled target diseases dataset (e.g., enteroscopy).具体而言，T_D专注于通过剩余的可转移性吸引瓶颈转移医疗病变的可转移视觉信息，同时忽略了无法转移的视觉特征。此外，T_F强调了如何增强各种病变的可转移语义特征，并自动忽略不可转移的表示形式，该表示探讨了域不变知识并回报可改善T_D的性能。最后，关于医学内窥镜数据集和几个非医学公共数据集的理论分析和广泛的实验很好地证明了我们提出的模型的优势。
Unsupervised domain adaptation has attracted growing research attention on semantic segmentation. However, 1) most existing models cannot be directly applied into lesions transfer of medical images, due to the diverse appearances of same lesion among different datasets; 2) equal attention has been paid into all semantic representations instead of neglecting irrelevant knowledge, which leads to negative transfer of untransferable knowledge. To address these challenges, we develop a new unsupervised semantic transfer model including two complementary modules (i.e., T_D and T_F ) for endoscopic lesions segmentation, which can alternatively determine where and how to explore transferable domain-invariant knowledge between labeled source lesions dataset (e.g., gastroscope) and unlabeled target diseases dataset (e.g., enteroscopy). Specifically, T_D focuses on where to translate transferable visual information of medical lesions via residual transferability-aware bottleneck, while neglecting untransferable visual characterizations. Furthermore, T_F highlights how to augment transferable semantic features of various lesions and automatically ignore untransferable representations, which explores domain-invariant knowledge and in return improves the performance of T_D. To the end, theoretical analysis and extensive experiments on medical endoscopic dataset and several non-medical public datasets well demonstrate the superiority of our proposed model.
