Inter-Semantic Domain Adversarial in Histopathological Images
This addresses data shift robustness for medical imaging applications, but it appears incremental as it adapts existing domain adversarial techniques to a new inter-semantic context.
The paper tackles the problem of data shift in histopathological images by demonstrating that domain adversarial methods can be harmful if misused, but they effectively transfer data shift invariance across datasets with different semantics, achieving performance similar to intra-semantic methods.
In computer vision, data shift has proven to be a major barrier for safe and robust deep learning applications. In medical applications, histopathological images are often associated with data shift and they are hardly available. It is important to understand to what extent a model can be made robust against data shift using all available data. Here, we first show that domain adversarial methods can be very deleterious if they are wrongly used. We then use domain adversarial methods to transfer data shift invariance from one dataset to another dataset with different semantics and show that domain adversarial methods are efficient inter-semantically with similar performance than intra-semantical domain adversarial methods.