Scalable Lipschitz Estimation for CNNs

arXiv:2403.18613v1 Announce Type: new
Abstract: Estimating the Lipschitz constant of deep neural networks is of growing interest as it is useful for informing on generalisability and adversarial robustness. Convolutional neural networks (CNNs) in particular, underpin much of the recent success in computer vision related applications. However, although existing methods for estimating the Lipschitz constant can be tight, they have limited scalability when applied to CNNs. To tackle this, we propose a novel method to accelerate Lipschitz constant estimation for CNNs. …

abstract adversarial applications arxiv cnns computer computer vision convolutional neural networks cs.lg however networks neural networks robustness scalable success type vision