Zobrazeno 1 - 10
of 429
pro vyhledávání: '"Karam, Lina"'
Autor:
Deng, Yingpeng, Karam, Lina J.
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular interest to
Externí odkaz:
http://arxiv.org/abs/2305.08000
Autor:
Deng, Yingpeng, Karam, Lina J.
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular interest to
Externí odkaz:
http://arxiv.org/abs/2104.10065
Autor:
Abdellatef, Hamdan, Karam, Lina J.
Publikováno v:
In Neural Networks January 2024 169:555-571
Autor:
Deng, Yingpeng, Karam, Lina J.
Although deep neural networks (DNNs) have been shown to be susceptible to image-agnostic adversarial attacks on natural image classification problems, the effects of such attacks on DNN-based texture recognition have yet to be explored. As part of ou
Externí odkaz:
http://arxiv.org/abs/2011.11957
Autor:
Deng, Yingpeng, Karam, Lina J.
Given the outstanding progress that convolutional neural networks (CNNs) have made on natural image classification and object recognition problems, it is shown that deep learning methods can achieve very good recognition performance on many texture d
Externí odkaz:
http://arxiv.org/abs/2010.01506
Autor:
Deng, Yingpeng, Karam, Lina J.
Researchers have shown that the predictions of a convolutional neural network (CNN) for an image set can be severely distorted by one single image-agnostic perturbation, or universal perturbation, usually with an empirically fixed threshold in the sp
Externí odkaz:
http://arxiv.org/abs/2003.05549
Autor:
Prakash, Charan D., Karam, Lina J.
Publikováno v:
Published in the IEEE Transactions on Image Processing, Vol. 30, 2021, pages 9220-9230
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 (GA
Externí odkaz:
http://arxiv.org/abs/1912.01707