Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published September 2014 | Published + Accepted Version
Book Section - Chapter Open

Bird Species Categorization Using Pose Normalized Deep Convolutional Nets

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%).

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.

Attached Files

Published - paper071.pdf

Accepted Version - 1406.2952.pdf

Files

paper071.pdf
Files (9.3 MB)
Name Size Download all
md5:ca45b9625861c9d4ccc67b7dbde6519b
5.2 MB Preview Download
md5:4803ac539ecebed094a3c40699c6aa96
4.1 MB Preview Download

Additional details

Created:
August 20, 2023
Modified:
October 20, 2023