Birdsnap: Large-Scale Fine-Grained Visual Categorization of Birds

• Published in: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 2019 - 2026
• Main Authors: Berg, Thomas, Jiongxin Liu, Seung Woo Lee, Alexander, Michelle L., Jacobs, David W., Belhumeur, Peter N.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Accuracy; Birds; Classifiers; Computer vision; Conferences; Estimation; Fine-grained visual categorization; Image recognition; Kernel; large-scale classification; Online; Pattern recognition; Production methods; Recognition; species identification; Training; Visual; Visualization
• ISSN: 1063-6919; 1063-6919; 2575-7075
• DOI: 10.1109/CVPR.2014.259

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.