Additionally, we show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges, allowing us to train a virtual sensor for fuel injection which is provably guaranteed to have at most 10. 69% relative error under noise while maintaining 3% relative error on non-adversarial data within normalized fuel injection ranges of 0. 6 to 1. 0.
In this work, we consider an alternative question: is it possible to fool deep classifiers, over all perceived objects of a certain type, by physically manipulating the camera itself?
In this paper, we propose a new threat model for adversarial attacks based on the Wasserstein distance.
To this end, we assume that the label set is the Cartesian product of totally ordered sets and the convex prior is separable.
Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks.
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier.
We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a 3D shape represented as a surface; the output is a continuous curve on the surface.
In this paper we propose a Fast Trust Region (FTR) approach for optimization of segmentation energies with nonlinear regional terms, which are known to be challenging for existing algorithms.