Deep Learning for Robust and Explainable Models in Computer Vision
It addresses critical issues for deploying reliable and trustworthy AI models in practical settings, though the work appears incremental as it builds on existing research in robustness and explainability.
This thesis tackles the challenges of robustness and explainability in deep learning models for computer vision, presenting methods that use feature response visualization to improve robustness and demonstrating applications in areas like medical imaging and affective computing.
Recent breakthroughs in machine and deep learning (ML and DL) research have provided excellent tools for leveraging enormous amounts of data and optimizing huge models with millions of parameters to obtain accurate networks for image processing. These developments open up tremendous opportunities for using artificial intelligence (AI) in the automation and human assisted AI industry. However, as more and more models are deployed and used in practice, many challenges have emerged. This thesis presents various approaches that address robustness and explainability challenges for using ML and DL in practice. Robustness and reliability are the critical components of any model before certification and deployment in practice. Deep convolutional neural networks (CNNs) exhibit vulnerability to transformations of their inputs, such as rotation and scaling, or intentional manipulations as described in the adversarial attack literature. In addition, building trust in AI-based models requires a better understanding of current models and developing methods that are more explainable and interpretable a priori. This thesis presents developments in computer vision models' robustness and explainability. Furthermore, this thesis offers an example of using vision models' feature response visualization (models' interpretations) to improve robustness despite interpretability and robustness being seemingly unrelated in the related research. Besides methodological developments for robust and explainable vision models, a key message of this thesis is introducing model interpretation techniques as a tool for understanding vision models and improving their design and robustness. In addition to the theoretical developments, this thesis demonstrates several applications of ML and DL in different contexts, such as medical imaging and affective computing.