70 citations · 135 across the 7 of their papers we have counts for
7 papers
Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images
Manohar Karki, Junghwan Cho, Seokhwan Ko
Data augmentation can effectively resolve a scarcity of images when training machine-learning algorithms. It can make them more robust to unseen images. We present a lesion conditi…
DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification
Qun Liu, Saikat Basu, Sangram Ganguly +4
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 i…
Pixel-level Reconstruction and Classification for Noisy Handwritten Bangla Characters
Manohar Karki, Qun Liu, Robert DiBiano +2
Classification techniques for images of handwritten characters are susceptible to noise. Quadtrees can be an efficient representation for learning from sparse features. In this pap…
Core Sampling Framework for Pixel Classification
Manohar Karki, Robert DiBiano, Saikat Basu +1
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,…
A Theoretical Analysis of Deep Neural Networks for Texture Classification
Saikat Basu, Manohar Karki, Robert DiBiano +4
We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative represe…
DeepSat - A Learning framework for Satellite Imagery
Saikat Basu, Sangram Ganguly, Supratik Mukhopadhyay +3
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 i…
Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets
Saikat Basu, Manohar Karki, Sangram Ganguly +3
Learning sparse feature representations is a useful instrument for solving an unsupervised learning problem. In this paper, we present three labeled handwritten digit datasets, col…