Open Access. Powered by Scholars. Published by Universities.®
![Digital Commons Network](http://assets.bepress.com/20200205/img/dcn/DCsunburst.png)
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Physical Sciences and Mathematics
Optimizing Uncertainty Quantification Of Vision Transformers In Deep Learning On Novel Ai Architectures, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja
Optimizing Uncertainty Quantification Of Vision Transformers In Deep Learning On Novel Ai Architectures, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja
Computer Science: Faculty Publications and Other Works
Deep Learning (DL) methods have shown substantial efficacy in computer vision (CV) and natural language processing (NLP). Despite their proficiency, the inconsistency in input data distributions can compromise prediction reliability. This study mitigates this issue by introducing uncertainty evaluations in DL models, thereby enhancing dependability through a distribution of predictions. Our focus lies on the Vision Transformer (ViT), a DL model that harmonizes both local and global behavior. We conduct extensive experiments on the ImageNet-1K dataset, a vast resource with over a million images across 1,000 categories. ViTs, while competitive, are vulnerable to adversarial attacks, making uncertainty estimation crucial for …
Optimized Uncertainty Estimation For Vision Transformers: Enhancing Adversarial Robustness And Performance Using Selective Classification, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja
Optimized Uncertainty Estimation For Vision Transformers: Enhancing Adversarial Robustness And Performance Using Selective Classification, Erik Pautsch, John Li, Silvio Rizzi, George K. Thiruvathukal, Maria Pantoja
Computer Science: Faculty Publications and Other Works
Deep Learning models often exhibit undue confidence when encountering out-of-distribution (OOD) inputs, misclassifying with high confidence. The ideal outcome, in these cases, would be an "I do not know" verdict. We enhance the trustworthiness of our models through selective classification, allowing the model to abstain from making predictions when facing uncertainty. Rather than a singular prediction, the model offers a prediction distribution, enabling users to gauge the model’s trustworthiness and determine the need for human intervention. We assess uncertainty in two baseline models: a Convolutional Neural Network (CNN) and a Vision Transformer (ViT). By leveraging these uncertainty values, we minimize …