Adaptive Domain Generalization for Digital Pathology Images
This addresses domain generalization for digital pathology, enabling more scalable deployment of AI models in histopathology by handling unseen shifts, though it appears incremental as it builds on existing test-time adaptation concepts.
The paper tackles the problem of domain shifts in digital pathology images, particularly 'invisible' shifts that degrade model performance, by proposing reactive domain generalization techniques that adapt at test-time without needing prior knowledge of the shifts, resulting in methods like test-time training to improve generalization without expensive annotations.
In AI-based histopathology, domain shifts are common and well-studied. However, this research focuses on stain and scanner variations, which do not show the full picture -- shifts may be combinations of other shifts, or "invisible" shifts that are not obvious but still damage performance of machine learning models. Furthermore, it is important for models to generalize to these shifts without expensive or scarce annotations, especially in the histopathology space and if wanting to deploy models on a larger scale. Thus, there is a need for "reactive" domain generalization techniques: ones that adapt to domain shifts at test-time rather than requiring predictions of or examples of the shifts at training time. We conduct a literature review and introduce techniques that react to domain shifts rather than requiring a prediction of them in advance. We investigate test time training, a technique for domain generalization that adapts model parameters at test-time through optimization of a secondary self-supervised task.