Analyzing Effects of Mixed Sample Data Augmentation on Model Interpretability

Abstract

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.

Accepted to Neural Networks

References in corpus (23)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• mixup: Beyond Empirical Risk Minimization
• Knowledge Distillation: A Survey
• Improved Regularization of Convolutional Neural Networks with Cutout
• Striving for Simplicity: The All Convolutional Net
• Interpretable Explanations of Black Boxes by Meaningful Perturbation
• When Does Label Smoothing Help?
• This Looks Like That: Deep Learning for Interpretable Image Recognition
• A Benchmark for Interpretability Methods in Deep Neural Networks
• Understanding the Role of Individual Units in a Deep Neural Network
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Concept Bottleneck Models
• SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
• Benchmarking Attribution Methods with Relative Feature Importance
• Towards Better Understanding Attribution Methods
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
• A Consistent and Efficient Evaluation Strategy for Attribution Methods
• The effectiveness of feature attribution methods and its correlation with automatic evaluation scores
• TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
• A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability
• RecursiveMix: Mixed Learning with History
• Visual correspondence-based explanations improve AI robustness and human-AI team accuracy