Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Sekeh, Salimeh Yasaei"'
Sparse deep neural networks (DNNs) excel in real-world applications like robotics and computer vision, by reducing computational demands that hinder usability. However, recent studies aim to boost DNN efficiency by trimming redundant neurons or filte
Externí odkaz:
http://arxiv.org/abs/2411.09199
Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks. However, their vulnerability to adversarial attacks, particularly through susceptible nodes, poses a
Externí odkaz:
http://arxiv.org/abs/2403.09901
In this paper, we present FogGuard, a novel fog-aware object detection network designed to address the challenges posed by foggy weather conditions. Autonomous driving systems heavily rely on accurate object detection algorithms, but adverse weather
Externí odkaz:
http://arxiv.org/abs/2403.08939
Despite the impressive performance of deep neural networks (DNNs), their computational complexity and storage space consumption have led to the concept of network compression. While DNN compression techniques such as pruning and low-rank decompositio
Externí odkaz:
http://arxiv.org/abs/2403.00155
The robustness of deep neural networks (DNNs) against adversarial attacks has been studied extensively in hopes of both better understanding how deep learning models converge and in order to ensure the security of these models in safety-critical appl
Externí odkaz:
http://arxiv.org/abs/2307.03803
Graph summarization is the problem of producing smaller graph representations of an input graph dataset, in such a way that the smaller compressed graphs capture relevant structural information for downstream tasks. There is a recent graph summarizat
Externí odkaz:
http://arxiv.org/abs/2305.07138
Autor:
Soucy, Nicholas, Sekeh, Salimeh Yasaei
Semantic segmentation models classifying hyperspectral images (HSI) are vulnerable to adversarial examples. Traditional approaches to adversarial robustness focus on training or retraining a single network on attacked data, however, in the presence o
Externí odkaz:
http://arxiv.org/abs/2210.16346
Autor:
Andle, Josh, Sekeh, Salimeh Yasaei
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data sequentially. CL performance evaluates the model's ability to continually learn and solve new problems with incremental available information over tim
Externí odkaz:
http://arxiv.org/abs/2204.12010
Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance, Efficiency, and Rob
Externí odkaz:
http://arxiv.org/abs/2204.07024
Several datasets exist which contain annotated information of individuals' trajectories. Such datasets are vital for many real-world applications, including trajectory prediction and autonomous navigation. One prominent dataset currently in use is th
Externí odkaz:
http://arxiv.org/abs/2203.11743