7 papers
Intelligent Multi-View Test Time Augmentation
Efe Ozturk, Mohit Prabhushankar, Ghassan AlRegib
In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint v…
Are Objective Explanatory Evaluation metrics Trustworthy? An Adversarial Analysis
Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib +1
Explainable AI (XAI) has revolutionized the field of deep learning by empowering users to have more trust in neural network models. The field of XAI allows users to probe the inner…
Explaining Representation Learning with Perceptual Components
Yavuz Yarici, Kiran Kokilepersaud, Mohit Prabhushankar +1
Self-supervised models create representation spaces that lack clear semantic meaning. This interpretability problem of representations makes traditional explainability methods inef…
Taxes Are All You Need: Integration of Taxonomical Hierarchy Relationships into the Contrastive Loss
Kiran Kokilepersaud, Yavuz Yarici, Mohit Prabhushankar +1
In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervise…
VOICE: Variance of Induced Contrastive Explanations to quantify Uncertainty in Neural Network Interpretability
Mohit Prabhushankar, Ghassan AlRegib
In this paper, we visualize and quantify the predictive uncertainty of gradient-based post hoc visual explanations for neural networks. Predictive uncertainty refers to the variabi…
Transitional Uncertainty with Layered Intermediate Predictions
Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib
In this paper, we discuss feature engineering for single-pass uncertainty estimation. For accurate uncertainty estimates, neural networks must extract differences in the feature sp…