51 citations · 245 across the 19 of their papers we have counts for
7 papers · 1 filter
Can the early human visual system compete with Deep Neural Networks?
Samuel Dodge, Lina Karam
We study and compare the human visual system and state-of-the-art deep neural networks on classification of distorted images. Different from previous works, we limit the display ti…
A Locally Weighted Fixation Density-Based Metric for Assessing the Quality of Visual Saliency Predictions
Milind S. Gide, Lina J. Karam
With the increased focus on visual attention (VA) in the last decade, a large number of computational visual saliency methods have been developed over the past few years. These mod…
A Study and Comparison of Human and Deep Learning Recognition Performance Under Visual Distortions
Samuel Dodge, Lina Karam
Deep neural networks (DNNs) achieve excellent performance on standard classification tasks. However, under image quality distortions such as blur and noise, classification accuracy…
DeepCorrect: Correcting DNN models against Image Distortions
Tejas Borkar, Lina Karam
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…
Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes
S. Alireza Golestaneh, Lina J. Karam
The detection of spatially-varying blur without having any information about the blur type is a challenging task. In this paper, we propose a novel effective approach to address th…
Quality Resilient Deep Neural Networks
Samuel Dodge, Lina Karam
We study deep neural networks for classification of images with quality distortions. We first show that networks fine-tuned on distorted data greatly outperform the original networ…
Visual Saliency Prediction Using a Mixture of Deep Neural Networks
Samuel Dodge, Lina Karam
Visual saliency models have recently begun to incorporate deep learning to achieve predictive capacity much greater than previous unsupervised methods. However, most existing model…