2 papers
cs.CV2025
Salient Information Preserving Adversarial Training Improves Clean and Robust Accuracy
Timothy Redgrave, Adam Czajka
In this work we introduce Salient Information Preserving Adversarial Training (SIP-AT), an intuitive method for relieving the robustness-accuracy trade-off incurred by traditional…
cs.LG2024
This Probably Looks Exactly Like That: An Invertible Prototypical Network
Zachariah Carmichael, Timothy Redgrave, Daniel Gonzalez Cedre +1
We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Protot…