Quantification in-the-wild: data-sets and baselines

TitleQuantification in-the-wild: data-sets and baselines
Publication TypeJournal Article
Year of Publication2015
AuthorsBeijbom, O., Hoffman J., Yao E., Darrell T., Rodriguez-Ramirez A., Gonzalez-Rivero M., & Hoegh-Guldberg O.
Published inCoRR
Volumeabs/1510.04811
Date Published10/2015
Abstract

Quantification is the task of estimating the class-distribution of a data-set. While typically considered as a parameter estimation problem with strict assumptions on the data-set shift, we consider quantification in-the-wild, on two large scale data-sets from marine ecology: a survey of Caribbean coral reefs, and a plankton time series from Martha's Vineyard Coastal Observatory. We investigate several quantification methods from the literature and indicate opportunities for future work. In particular, we show that a deep neural network can be fine-tuned on a very limited amount of data (25 - 100 samples) to outperform alternative methods.

URLhttp://www.icsi.berkeley.edu/pubs/vision/quantificationinthewild15.pdf
ICSI Research Group

Vision