Related papers: Multilevel Robustness for 2D Vector Field Feature …
We present a new approach to assessing the robustness of neural networks based on estimating the proportion of inputs for which a property is violated. Specifically, we estimate the probability of the event that the property is violated…
To obtain effective pedestrian detection results in surveillance video, there have been many methods proposed to handle the problems from severe occlusion, pose variation, clutter background, \emph{etc}. Besides detection accuracy, a robust…
Dynamic race detection is a highly effective runtime verification technique for identifying data races by instrumenting and monitoring concurrent program runs. However, standard dynamic race detection is incompatible with practical weak…
We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical…
The dissertation presents four key contributions toward fairness and robustness in vision learning. First, to address the problem of large-scale data requirements, the dissertation presents a novel Fairness Domain Adaptation approach…
Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…
We formalize notions of robustness for composite estimators via the notion of a breakdown point. A composite estimator successively applies two (or more) estimators: on data decomposed into disjoint parts, it applies the first estimator on…
Visual place recognition (VPR) capabilities enable autonomous robots to navigate complex environments by discovering the environment's topology based on visual input. Most research efforts focus on enhancing the accuracy and robustness of…
This paper introduces a simple but highly efficient ensemble for robust texture classification, which can effectively deal with translation, scale and changes of significant viewpoint problems. The proposed method first inherits the spirit…
Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost.…
Periodicity detection is a crucial step in time series tasks, including monitoring and forecasting of metrics in many areas, such as IoT applications and self-driving database management system. In many of these applications, multiple…
Recently, there has been a significant interest in performing convolution over irregularly sampled point clouds. Since point clouds are very different from regular raster images, it is imperative to study the generalization of the…
Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative trackers. However, due to the drastic difference between image…
Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They are studied in several communities, including synthetic corruption benchmarks for…
Many critical infrastructure systems have network structure and are under stress. Despite their national importance, the complexity of large-scale transport networks means we do not fully understand their vulnerabilities to cascade…
In turbulent flows, energy production is associated with highly organized structures, known as coherent structures. Since these structures are three-dimensional, their detection remains challenging in the most common situation, when…
Functional data analysis offers a diverse toolkit of statistical methods tailored for analyzing samples of real-valued random functions. Recently, samples of time-varying random objects, such as time-varying networks, have been increasingly…
Particle tracking is a powerful biophysical tool that requires conversion of large video files into position time series, i.e. traces of the species of interest for data analysis. Current tracking methods, based on a limited set of input…
The paper deals with local robust feedback synthesis for systems with multidimensional control and unknown bounded perturbations. Using V.~I.~Korobov's controllability function method, we construct a bounded control which steers an…
We study the robustness of system estimation to parametric perturbations in system dynamics and initial conditions. We define the problem of sensitivity-based parametric uncertainty quantification in dynamical system estimation. The main…