To better conform to data geometry, recent deep generative modelling techniques adapt Euclidean constructions to non-Euclidean spaces.
Recent advances in deep representation learning on Riemannian manifolds extend classical deep learning operations to better capture the geometry of the manifold.
We show that we can select a layer of the source model to perturb without any knowledge of the target models while achieving high transferability.
We introduce Fashion++, an approach that proposes minimal adjustments to a full-body clothing outfit that will have maximal impact on its fashionability.
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models.
Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain.
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models.