In this paper, we present a patch-based land use and land cover classification approach
using Sentinel-2 satellite images. The Sentinel-2 satellite images are openly and freely …

The success of deep learning in vision can be attributed to:(a) models with high capacity;(b)
increased computational power; and (c) availability of large-scale labeled data. Since 2012 …

In recent years, research in applying optimization approaches in the automatic design of
deep neural networks has become increasingly popular. Although various approaches have …

Pre-training general-purpose visual features with convolutional neural networks without
relying on annotations is a challenging and important task. Most recent efforts in …

This paper explores a simple and efficient baseline for text classification. Our experiments
show that our fast text classifier fastText is often on par with deep learning classifiers in terms …

Convolutional networks trained on large supervised datasets produce visual features which
form the basis for the state-of-the-art in many computer-vision problems. Further …

Training machine learning (ML) models with large datasets can incur significant resource
contention on shared clusters. This training typically involves many iterations that continually …

Unsupervised image-to-image translation techniques are able to map local texture between
two domains, but they are typically un-successful when the domains require larger shape …

We introduce a novel approach for annotating large quantity of in-the-wild facial images with
high-quality posterior age distribution as labels. Each posterior provides a probability …

Recent successes of deep learning have been largely driven by the ability to train large
models on vast amounts of data. We believe that High Performance Computing (HPC) will …