Improved Bird Species Recognition Using Pose Normalized Deep Convolutional Nets

Steve Branson, Grant Van Horn, Pietro Perona and Serge Belongie

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.87

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~\cite{krizhevsky2012imagenet,donahue2013decaf,girshick2013rich,Jia13caffe} 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\%).

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 134K)
Paper (PDF, 14 pages, 4.9M)
Bibtex File

Citation

BibTex