CaltechAUTHORS
  A Caltech Library Service

Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

Branson, Steve and Van Horn, Grant and Belongie, Serge and Perona, Pietro (2014) Bird Species Categorization Using Pose Normalized Deep Convolutional Nets. In: Proceedings of the British Machine Vision Conference 2014. BMVA Press , Durham, UK, Art. No. 71. ISBN 1-901725-52-9. https://resolver.caltech.edu/CaltechAUTHORS:20190327-085910235

[img] PDF - Published Version
See Usage Policy.

4Mb
[img] PDF - Accepted Version
See Usage Policy.

4006Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190327-085910235

Abstract

We propose an architecture for fine-grained visual categorization that approaches expert human performance in the classification of bird species. Our architecture first computes an estimate of the object's pose; this is used to compute local image features which are, in turn, used for classification. The features are computed by applying deep convolutional nets to image patches that are located and normalized by the pose. We perform an empirical study of a number of pose normalization schemes, including an investigation of higher order geometric warping functions. We propose a novel graph-based clustering algorithm for learning a compact pose normalization space. We perform a detailed investigation of state-of-the-art deep convolutional feature implementations and fine-tuning feature learning for fine-grained classification. We observe that a model that integrates lower-level feature layers with pose-normalized extraction routines and higher-level feature layers with unaligned image features works best. Our experiments advance state-of-the-art performance on bird species recognition, with a large improvement of correct classification rates over previous methods (75% vs. 55-65%).


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://dx.doi.org/10.5244/C.28.87DOIArticle
http://arxiv.org/abs/1406.2952arXivDiscussion Paper
ORCID:
AuthorORCID
Belongie, Serge0000-0002-0388-5217
Perona, Pietro0000-0002-7583-5809
Alternate Title:Improved Bird Species Recognition Using Pose Normalized Deep Convolutional Nets
Additional Information:© 2014. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. This work is supported by a Google Focused Research Award.
Funders:
Funding AgencyGrant Number
GoogleUNSPECIFIED
Record Number:CaltechAUTHORS:20190327-085910235
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190327-085910235
Official Citation:Steve Branson, Grant Van Horn, Pietro Perona, and Serge Belongie. Improved Bird Species Recognition Using Pose Normalized Deep Convolutional Nets. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94198
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:27 Mar 2019 17:53
Last Modified:03 Oct 2019 21:01

Repository Staff Only: item control page