Do We Need More Training Data?

August 2016

Do We Need More Training Data?

Authors:

X. Zhu, C. Vondrick, C. Fowlkes, and D. Ramanan

Abstract:

Datasets for training object recognition systems are steadily increasing in size. This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model complexity and the Bayes risk associated with the feature spaces in which they operate. We focus on the popular paradigm of discriminatively trained templates defined on oriented gradient features. We investigate the performance of mixtures of templates as the number of mixture components and the amount of training data grows. Surprisingly, even with proper treatment of regularization and "outliers", the performance of classic mixture models appears to saturate quickly ($${\sim }10$$~10 templates and $${\sim }100$$~100 positive training examples per template). This is not a limitation of the feature space as compositional mixtures that share template parameters via parts and that can synthesize new templates not encountered during training yield significantly better performance. Based on our analysis, we conjecture that the greatest gains in detection performance will continue to derive from improved representations and learning algorithms that can make efficient use of large datasets.
@article{Zhu-2016-121105,
author = {X. Zhu And C. Vondrick And C. Fowlkes And D. Ramanan},
title = {Do We Need More Training Data?},
journal = {Proceedings of International Journal of Computer Vision},
year = {2016},
month = {August},
volume = {119},
number = {1},
pages = {76 - 92},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.