Match!
Lina J. Karam
Arizona State University
245Publications
29H-index
4,141Citations
Publications 236
Newest
#1Tejas S. Borkar (ASU: Arizona State University)H-Index: 1
#2Lina J. Karam (ASU: Arizona State University)H-Index: 29
In recent years, the widespread use of deep neural networks (DNNs) has facilitated great improvements in performance for computer vision tasks like image classification and object recognition. In most realistic computer vision applications, an input image undergoes some form of image distortion such as blur and additive noise during image acquisition or transmission. Deep networks trained on pristine images perform poorly when tested on such distortions. In this paper, we evaluate the effect of ...
10 CitationsSource
#1Jinane Mounsef (ASU: Arizona State University)H-Index: 1
#2Lina J. Karam (ASU: Arizona State University)H-Index: 29
In the last two decades, numerous methods have been developed to offer a formulation to the face recognition problem under scene-dependent conditions. However, these methods have not considered image quality degradations resulting from capture, processing, and transmission such as blur and occlusion due to packet loss, under the same scene variations. Although deep neural networks are achieving state-of-the-art results on face recognition, the existing networks are susceptible to quality distort...
Source
Oct 9, 2019 in FM (Formal Methods)
#1Mohammad Hekmatnejad (ASU: Arizona State University)H-Index: 1
#2Shakiba Yaghoubi (ASU: Arizona State University)H-Index: 5
Last.Georgios Fainekos (ASU: Arizona State University)H-Index: 26
view all 7 authors...
As Automated Vehicles (AV) get ready to hit the public roads unsupervised, many practical questions still remain open. For example, there is no commonly acceptable formal definition of what safe driving is. A formal definition of safe driving can be utilized in developing the vehicle behaviors as well as in certification and legal cases. Toward that goal, the Responsibility-Sensitive Safety (RSS) model was developed as a first step toward formalizing safe driving behavior upon which the broader ...
Source
#1Samuel Dodge (ASU: Arizona State University)H-Index: 5
#2Lina J. Karam (ASU: Arizona State University)H-Index: 29
Image quality is an important practical challenge that is often overlooked in the design of machine vision systems. Commonly, machine vision systems are trained and tested on high-quality image datasets, yet in practical applications the input images cannot be assumed to be of high quality. Modern deep neural networks (DNNs) have been shown to perform poorly on images affected by blur or noise distortions. In this work, we investigate whether human subjects also perform poorly on distorted stimu...
2 CitationsSource
Jul 1, 2019 in ICME (International Conference on Multimedia and Expo)
#1Lina J. KaramH-Index: 29
Last.Feng Wu (USTC: University of Science and Technology of China)H-Index: 38
view all 3 authors...
Source
#1Tejas S. Borkar (ASU: Arizona State University)H-Index: 1
#2Felix Heide (Princeton University)H-Index: 17
Last.Lina J. Karam (ASU: Arizona State University)H-Index: 29
view all 3 authors...
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturbations added to any image can fool a target network into making erroneous predictions. Departing from existing defense strategies that work mostly in the image domain, we present a novel defense which operates in the DNN feature domain and effectively defends against such universal perturbations. Our approach identifies...
#1Charan D. Prakash (ASU: Arizona State University)H-Index: 2
#2Farshad Akhbari (Intel)H-Index: 2
Last.Lina J. Karam (ASU: Arizona State University)H-Index: 29
view all 3 authors...
Abstract This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90% more true positives per frame compared to one of the state-of-the-art methods. Our proposed ...
2 CitationsSource
#1Tejas S. Borkar (ASU: Arizona State University)H-Index: 1
#2Felix Heide (Princeton University)H-Index: 17
Last.Lina J. Karam (ASU: Arizona State University)H-Index: 29
view all 3 authors...
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, so-called universal adversarial perturbations are image-agnostic perturbations that can be added to any image and can fool a target network into making erroneous predictions. Departing from existing adversarial defense strategies, which work in the image domain, we present a novel defense which operates in the DNN feature domain and effectively defends against such...
#1Charan D. Prakash (ASU: Arizona State University)H-Index: 2
#2Lina J. Karam (ASU: Arizona State University)H-Index: 29
In this paper, we propose in our novel generative framework the use of Generative Adversarial Networks (GANs) to generate features that provide robustness for object detection on reduced quality images. The proposed GAN-based Detection of Objects (GAN-DO) framework is not restricted to any particular architecture and can be generalized to several deep neural network (DNN) based architectures. The resulting deep neural network maintains the exact architecture as the selected baseline model withou...
#1Samuel Dodge (ASU: Arizona State University)H-Index: 5
#2Lina J. Karam (ASU: Arizona State University)H-Index: 29
We study deep neural networks for classification of images with quality distortions. Deep network performance on poor quality images can be greatly improved if the network is fine-tuned with distorted data. However, it is difficult for a single fine-tuned network to perform well across multiple distortion types. We propose a mixture of experts-based ensemble method, MixQualNet, that is robust to multiple different types of distortions. The “experts” in our model are trained on a particular type ...
2 CitationsSource
12345678910