Search Results for author:
Found 13 papers, 3 papers with code
Fast Trust Region for Segmentation
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.
An Experimental Comparison of Trust Region and Level Sets
High-order (non-linear) functionals have become very popular in segmentation, stereo and other computer vision problems.
Video Segmentation With Just a Few Strokes
As the use of videos is becoming more popular in computer vision, the need for annotated video datasets increases.
Efficient Globally Optimal 2D-to-3D Deformable Shape Matching
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.
A Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching
We propose a combinatorial solution for the problem of non-rigidly matching a 3D shape to 3D image data.
Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier.
Scaling provable adversarial defenses
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.
MRF Optimization with Separable Convex Prior on Partially Ordered Labels
To this end, we assume that the label set is the Cartesian product of totally ordered sets and the convex prior is separable.
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
In this paper, we propose a new threat model for adversarial attacks based on the Wasserstein distance.
Adversarial camera stickers: A physical camera-based attack on deep learning systems
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?
Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications
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.
Universe Points Representation Learning for Partial Multi-Graph Matching
Many challenges from natural world can be formulated as a graph matching problem.
Ranked #1 on
Graph Matching
on CUB
Adaptive Certified Training: Towards Better Accuracy-Robustness Tradeoffs
Existing certified training methods produce models that achieve high provable robustness guarantees at certain perturbation levels.
