Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability
This addresses the problem of maintaining interpretability in deep learning models for applications relying on attribution maps, though it is incremental as it builds on existing augmentation studies.
The paper investigates how mixed sample data augmentation affects model interpretability, specifically feature attribution maps, and finds that several such augmentations decrease interpretability, with label mixing playing a significant role.
Mixed sample data augmentation strategies are actively used when training deep neural networks (DNNs). Recent studies suggest that they are effective at various tasks. However, the impact of mixed sample data augmentation on model interpretability has not been widely studied. In this paper, we explore the relationship between model interpretability and mixed sample data augmentation, specifically in terms of feature attribution maps. To this end, we introduce a new metric that allows a comparison of model interpretability while minimizing the impact of occlusion robustness of the model. Experimental results show that several mixed sample data augmentation decreases the interpretability of the model and label mixing during data augmentation plays a significant role in this effect. This new finding suggests it is important to carefully adopt the mixed sample data augmentation method, particularly in applications where attribution map-based interpretability is important.