Bridging Contrastive Learning and Domain Adaptation: Theoretical Perspective and Practical Application
This work addresses domain adaptation challenges in medical imaging, specifically for mammography, but is incremental as it builds on existing theoretical frameworks.
The paper tackles the problem of connecting contrastive learning with domain adaptation by showing that minimizing contrastive losses reduces a domain dissimilarity measure and improves class-separability, with experiments on mammography datasets demonstrating enhanced domain adaptation and classification performance.
This work studies the relationship between Contrastive Learning and Domain Adaptation from a theoretical perspective. The two standard contrastive losses, NT-Xent loss (Self-supervised) and Supervised Contrastive loss, are related to the Class-wise Mean Maximum Discrepancy (CMMD), a dissimilarity measure widely used for Domain Adaptation. Our work shows that minimizing the contrastive losses decreases the CMMD and simultaneously improves class-separability, laying the theoretical groundwork for the use of Contrastive Learning in the context of Domain Adaptation. Due to the relevance of Domain Adaptation in medical imaging, we focused the experiments on mammography images. Extensive experiments on three mammography datasets - synthetic patches, clinical (real) patches, and clinical (real) images - show improved Domain Adaptation, class-separability, and classification performance, when minimizing the Supervised Contrastive loss.