J
Jana Kosecka
Researcher at George Mason University
Publications - 166
Citations - 10467
Jana Kosecka is an academic researcher from George Mason University. The author has contributed to research in topics: Object detection & Motion estimation. The author has an hindex of 45, co-authored 155 publications receiving 9087 citations. Previous affiliations of Jana Kosecka include Austrian Institute of Technology & University of Pennsylvania.
Papers
More filters
Proceedings ArticleDOI
Diverse Knowledge Distillation (DKD): A Solution for Improving The Robustness of Ensemble Models Against Adversarial Attacks
TL;DR: In this article, the loss function is regulated by a reverse knowledge distillation, forcing the new member to learn different features and map to a latent space safely distanced from those of existing members.
Proceedings ArticleDOI
Motion estimation in computer vision: optimization on Stiefel manifolds
TL;DR: It is shown that the proposed nonlinear algorithms converge very rapidly (with quadratic rate of convergence) as long as the conventional SVD based eight-point linear algorithm has a unique solution.
Posted Content
Learning Local RGB-to-CAD Correspondences for Object Pose Estimation.
TL;DR: This paper solves the key problem of existing methods requiring expensive 3D pose annotations by proposing a new method that matches RGB images to CAD models for object pose estimation and can reliably estimate object pose in RGB images and generalize to object instances not seen during training.
Proceedings ArticleDOI
Communication enhanced navigation strategies for teams of mobile agents
TL;DR: This paper will examine control strategies that in the absence of the global model of the environment can substantially improve the performance of the team using additional sensing and communication capabilities.
Proceedings ArticleDOI
Introspective semantic segmentation
Gautam Singh,Jana Kosecka +1 more
TL;DR: This work quantifies the confidence of the region classifiers in the context of a non-parametric k-nearest neighbor (k-NN) framework for semantic segmentation by using the so called strangeness measure.