Birdsnap: Large-scale Fine-grained Visual Categorization of Birds

Thomas Berg, Jiongxin Liu, Seung Woo Lee, Michelle L. Alexander, David W. Jacobs, Peter N. Belhumeur; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 2011-2018

Abstract


We address the problem of large-scale fine-grained visual categorization, describing new methods we have used to produce an online field guide to 500 North American bird species. We focus on the challenges raised when such a system is asked to distinguish between highly similar species of birds. First, we introduce "one-vs-most classifiers." By eliminating highly similar species during training, these classifiers achieve more accurate and intuitive results than common one-vs-all classifiers. Second, we show how to estimate spatio-temporal class priors from observations that are sampled at irregular and biased locations. We show how these priors can be used to significantly improve performance. We then show state-of-the-art recognition performance on a new, large dataset that we make publicly available. These recognition methods are integrated into the online field guide, which is also publicly available.

Related Material


[pdf]
[bibtex]
@InProceedings{Berg_2014_CVPR,
author = {Berg, Thomas and Liu, Jiongxin and Woo Lee, Seung and Alexander, Michelle L. and Jacobs, David W. and Belhumeur, Peter N.},
title = {Birdsnap: Large-scale Fine-grained Visual Categorization of Birds},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2014}
}