1 code implementation • CVPR 2020 • Tejas Borkar, Felix Heide, Lina Karam
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations.
no code implementations • 21 Apr 2018 • S. Alireza Golestaneh, Lina Karam
Performance evaluations on two synthesized texture databases demonstrate that our proposed RR synthesized texture quality metric significantly outperforms both full-reference and RR state-of-the-art quality metrics in predicting the perceived visual quality of the synthesized textures.
no code implementations • 12 Mar 2018 • Aditee Shrotre, Lina Karam
To compare the performance of the proposed quality index with existing image quality assessment measures, we construct two different datasets consisting of reconstructed background images and corresponding subjective scores.
no code implementations • 8 Jan 2018 • Lina Karam, Tejas Borkar, Yu Cao, Junseok Chae
The proposed generative sensing framework aims at transforming low-end, low-quality sensor data into higher quality sensor data in terms of achieved classification accuracy.
no code implementations • 12 Oct 2017 • 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.
no code implementations • 6 May 2017 • Samuel Dodge, Lina Karam
In this work, we compare the performance of DNNs with human subjects on distorted images.
1 code implementation • 5 May 2017 • Tejas Borkar, Lina Karam
In this paper, we evaluate the effect of image distortions like Gaussian blur and additive noise on the activations of pre-trained convolutional filters.
no code implementations • 23 Mar 2017 • Samuel Dodge, Lina Karam
The "experts" in our model are trained on a particular type of distortion.
no code implementations • 1 Feb 2017 • Samuel Dodge, Lina Karam
The final saliency map is computed as a weighted mixture of the expert networks' output, with weights determined by a separate gating network.
4 code implementations • 14 Apr 2016 • Samuel Dodge, Lina Karam
We show that the existing networks are susceptible to these quality distortions, particularly to blur and noise.