Unsupervised Domain Adaptation via Similarity-based Prototypes for Cross-Modality Segmentation
This addresses domain adaptation for cross-modality segmentation, which is important for medical imaging and autonomous systems, but appears incremental as it builds on existing prototype-based approaches.
The paper tackles the problem of performance degradation in deep learning models when applied to unseen data due to domain shift, proposing a framework for cross-modality segmentation that uses similarity-based prototypes and dictionaries to improve representation and separability. The method achieves better results than state-of-the-art methods in experiments.
Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised domain adaptation attempts to reduce the domain gap and avoid costly annotation of unseen domains. This paper proposes a novel framework for cross-modality segmentation via similarity-based prototypes. In specific, we learn class-wise prototypes within an embedding space, then introduce a similarity constraint to make these prototypes representative for each semantic class while separable from different classes. Moreover, we use dictionaries to store prototypes extracted from different images, which prevents the class-missing problem and enables the contrastive learning of prototypes, and further improves performance. Extensive experiments show that our method achieves better results than other state-of-the-art methods.