期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 40, 期 1, 页码 154-165出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2020.3023466
关键词
Image segmentation; Semantics; Task analysis; Feature extraction; Microscopy; Training; Adaptation models; Unsupervised domain adaptation; instance segmentation; microscopy images
In this work, we propose a Panoptic Domain Adaptive Mask R-CNN (PDAM) method for unsupervised instance segmentation in microscopy images. By integrating semantic- and instance-level feature adaptation, our method effectively aligns cross-domain features at the panoptic level and solves domain bias issues. Experimental results demonstrate that the PDAM method outperforms state-of-the-art UDA methods by a large margin in various scenarios.
In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images. Since there currently lack methods particularly for UDA instance segmentation, we first design a Domain Adaptive Mask R-CNN (DAM) as the baseline, with cross-domain feature alignment at the image and instance levels. In addition to the image- and instance-level domain discrepancy, there also exists domain bias at the semantic level in the contextual information. Next, we, therefore, design a semantic segmentation branch with a domain discriminator to bridge the domain gap at the contextual level. By integrating the semantic- and instance-level feature adaptation, our method aligns the cross-domain features at the panoptic level. Third, we propose a task re-weighting mechanism to assign trade-off weights for the detection and segmentation loss functions. The task re-weighting mechanism solves the domain bias issue by alleviating the task learning for some iterations when the features contain source-specific factors. Furthermore, we design a feature similarity maximization mechanism to facilitate instance-level feature adaptation from the perspective of representational learning. Different from the typical feature alignment methods, our feature similarity maximization mechanism separates the domain-invariant and domain-specific features by enlarging their feature distribution dependency. Experimental results on three UDA instance segmentation scenarios with five datasets demonstrate the effectiveness of our proposed PDAM method, which outperforms state-of-the-art UDA methods by a large margin.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据