Current methods for learning visual categories work well when a large amount of labeled data is available, but can run into severe difficulties when the number of labeled examples...
We investigate a biologically motivated approach to fast visual classification, directly inspired by the recent work [13]. Specifically, trading-off biological accuracy for comput...
We investigate how to organize a large collection of geotagged photos, working with a dataset of about 35 million images collected from Flickr. Our approach combines content analy...
David J. Crandall, Lars Backstrom, Daniel P. Hutte...
Abstract In case of insufficient data samples in highdimensional classification problems, sparse scatters of samples tend to have many ‘holes’—regions that have few or no nea...
Hakan Cevikalp, Diane Larlus, Marian Neamtu, Bill ...
Remote sensing of terrain characteristics is an important component for autonomous operation of mobile robots in natural terrain. Often this involves classification of terrain int...