Source-Relaxed Domain Adaptation for Image Segmentation

Domain adaptation (DA) has drawn high interests for its capacity to adapt a model trained on labeled source data to perform well on unlabeled or weakly labeled target data from a different domain. Most common DA techniques require the concurrent access to the input images of both the source and target domains. However, in practice, it is common that the source images are not available in the adaptation phase. This is a very frequent DA scenario in medical imaging, for instance, when the source and target images come from different clinical sites. We propose a novel formulation for adapting segmentation networks, which relaxes such a constraint. Our formulation is based on minimizing a label-free entropy loss defined over target-domain data, which we further guide with a domain invariant prior on the segmentation regions. Many priors can be used, derived from anatomical information. Here, a class-ratio prior is learned via an auxiliary network and integrated in the form of a Kullback-Leibler (KL) divergence in our overall loss function. We show the effectiveness of our prior-aware entropy minimization in adapting spine segmentation across different MRI modalities. Our method yields comparable results to several state-of-the-art adaptation techniques, even though is has access to less information, the source images being absent in the adaptation phase. Our straight-forward adaptation strategy only uses one network, contrary to popular adversarial techniques, which cannot perform without the presence of the source images. Our framework can be readily used with various priors and segmentation problems.

[1]  Cheng Chen,et al.  PnP-AdaNet: Plug-and-Play Adversarial Domain Adaptation Network at Unpaired Cross-Modality Cardiac Segmentation , 2019, IEEE Access.

[2]  Kurt Keutzer,et al.  A Novel Domain Adaptation Framework for Medical Image Segmentation , 2018, BrainLes@MICCAI.

[3]  Konstantinos Kamnitsas,et al.  Unsupervised domain adaptation in brain lesion segmentation with adversarial networks , 2016, IPMI.

[4]  Luc Van Gool,et al.  ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Tolga Tasdizen,et al.  Domain adaptation for biomedical image segmentation using adversarial training , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[6]  Eric Granger,et al.  Constrained‐CNN losses for weakly supervised segmentation☆ , 2018, Medical Image Anal..

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Patrick Pérez,et al.  ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Yoshua Bengio,et al.  Semi-supervised Learning by Entropy Minimization , 2004, CAP.

[10]  Xinlei Chen,et al.  Prior-Aware Neural Network for Partially-Supervised Multi-Organ Segmentation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.

[12]  Yang Zou,et al.  Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training , 2018, ArXiv.

[13]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[14]  Taesung Park,et al.  CyCADA: Cycle-Consistent Adversarial Domain Adaptation , 2017, ICML.

[15]  Philip David,et al.  A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Li Cheng,et al.  Supervised Segmentation of Un-Annotated Retinal Fundus Images by Synthesis , 2019, IEEE Transactions on Medical Imaging.

[17]  Ming-Hsuan Yang,et al.  Learning to Adapt Structured Output Space for Semantic Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Jose Dolz,et al.  Constrained domain adaptation for segmentation , 2019, MICCAI.

[20]  Amar Mitiche,et al.  Deep Clustering: On the Link Between Discriminative Models and K-Means , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Andreas Krause,et al.  Discriminative Clustering by Regularized Information Maximization , 2010, NIPS.

[23]  Vittorio Murino,et al.  Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation , 2017, ICLR.

[24]  Chunming Zhao,et al.  Entropy Minimization Versus Diversity Maximization for Domain Adaptation , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[25]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[26]  Ming Yang,et al.  Conditional Generative Adversarial Network for Structured Domain Adaptation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.