Presentation

· Contributors · Organizations · Search Program · My Schedule · Happening Now · Maps

This content is available for: Workshop Reg Pass. Upgrade Registration

Optimized Uncertainty Estimation for Vision Transformers: Enhancing Adversarial Robustness and Performance Using Selective Classification

Session1st Workshop on Enabling Predictive Science with Optimization and Uncertainty Quantification in HPC

DescriptionDeep Learning models frequently produce high-confidence softmax outputs for out-of-distribution (OOD) inputs, which would ideally be classified as "I don't know". To enhance our model's trustworthiness, we incorporate selective classification, which entails abstaining from predictions in situations of doubt. This approach requires initial uncertainty estimation. Subsequently, instead of offering a singular prediction, we provide a distribution over predictions, enabling users to discern if the model is trustworthy or if consultation with a human expert is necessary. In this paper, we assess uncertainty in two baseline models: a Convolutional Neural Network (CNN) and a Vision Transformer (ViT). Leveraging these uncertainty values, we minimize errors by refraining from predictions during high uncertainty. Additionally, we evaluate these models across various distributed architectures.

Author/Presenters