Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation

Abstract

To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning. However, such category-agnostic global alignment lacks of exploiting the class-level joint distributions, causing the aligned distribution less discriminative. To address this issue, we propose in this paper a novel margin preserving self-paced contrastive Learning (MPSCL) model for cross-modal medical image segmentation. Unlike the conventional construction of contrastive pairs in contrastive learning, the domain-adaptive category prototypes are utilized to constitute the positive and negative sample pairs. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. To enhance the supervision for contrastive learning, more informative pseudo-labels are generated in target domain in a self-paced way, thus benefiting the category-aware distribution alignment for UDA. Furthermore, the domain-invariant representations are learned through joint contrastive learning between the two domains. Extensive experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance, and outperforms a wide variety of state-of-the-art methods by a large margin.

arXiv commentThis manuscript has been accepted by by IEEE JBHI and the code is available in https://github.com/TFboys-lzz/MPSCL

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Distilling the Knowledge in a Neural Network
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• A Simple Framework for Contrastive Learning of Visual Representations
• Learning Transferable Features with Deep Adaptation Networks
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images
• Self-Training for End-to-End Speech Recognition
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• Revisiting Self-Training for Neural Sequence Generation
• Supervised Contrastive Learning
• Unsupervised Learning for Cell-level Visual Representation in Histopathology Images with Generative Adversarial Networks
• Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
• Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis

Cited by in corpus (3)

• Medical Image Classification Using Transfer Learning and Chaos Game Optimization on the Internet of Medical Things
• Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels
• TCSA-UDA: Text-Driven Cross-Semantic Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation