Zobrazeno 1 - 10
of 37
pro vyhledávání: '"DiBiano, Robert"'
Autor:
Mukhopadhyay, Supratik, Liu, Qun, Collier, Edward, Zhu, Yimin, Gudishala, Ravindra, Chokwitthaya, Chanachok, DiBiano, Robert, Nabijiang, Alimire, Saeidi, Sanaz, Sidhanta, Subhajit, Ganguly, Arnab
Recently, it has been widely accepted by the research community that interactions between humans and cyber-physical infrastructures have played a significant role in determining the performance of the latter. The existing paradigm for designing cyber
Externí odkaz:
http://arxiv.org/abs/2001.01918
Autor:
Liu, Qun, Basu, Saikat, Ganguly, Sangram, Mukhopadhyay, Supratik, DiBiano, Robert, Karki, Manohar, Nemani, Ramakrishna
Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches
Externí odkaz:
http://arxiv.org/abs/1911.07747
Classification techniques for images of handwritten characters are susceptible to noise. Quadtrees can be an efficient representation for learning from sparse features. In this paper, we improve the effectiveness of probabilistic quadtrees by using a
Externí odkaz:
http://arxiv.org/abs/1806.08037
Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the higher layers
Externí odkaz:
http://arxiv.org/abs/1804.07846
Autor:
DiBiano, Robert Jacob
More complex image understanding algorithms are increasingly practical in a host of emerging applications. Object tracking has value in surveillance and data farming; and object recognition has applications in surveillance, data management, and indus
Externí odkaz:
http://etd.lsu.edu/docs/available/etd-10022015-140942/
The intermediate map responses of a Convolutional Neural Network (CNN) contain information about an image that can be used to extract contextual knowledge about it. In this paper, we present a core sampling framework that is able to use these activat
Externí odkaz:
http://arxiv.org/abs/1612.01981
Autor:
Basu, Saikat, Karki, Manohar, DiBiano, Robert, Mukhopadhyay, Supratik, Ganguly, Sangram, Nemani, Ramakrishna, Gayaka, Shreekant
We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space f
Externí odkaz:
http://arxiv.org/abs/1605.02699
Autor:
Basu, Saikat, Ganguly, Sangram, Mukhopadhyay, Supratik, DiBiano, Robert, Karki, Manohar, Nemani, Ramakrishna
Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches
Externí odkaz:
http://arxiv.org/abs/1509.03602
Autor:
Basu, Saikat, Karki, Manohar, Ganguly, Sangram, DiBiano, Robert, Mukhopadhyay, Supratik, Nemani, Ramakrishna
Learning sparse feature representations is a useful instrument for solving an unsupervised learning problem. In this paper, we present three labeled handwritten digit datasets, collectively called n-MNIST. Then, we propose a novel framework for the c
Externí odkaz:
http://arxiv.org/abs/1509.03413
Autor:
Basu, Saikat, Mukhopadhyay, Supratik, Karki, Manohar, DiBiano, Robert, Ganguly, Sangram, Nemani, Ramakrishna, Gayaka, Shreekant
Publikováno v:
In Neural Networks January 2018 97:173-182
