Bird species categorization using pose normalized deep convolutional nets
Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt
Standard
Bird species categorization using pose normalized deep convolutional nets. / Branson, Steve; Van Horn, Grant; Belongie, Serge; Perona, Pietro.
2014. Paper præsenteret ved 25th British Machine Vision Conference, BMVC 2014, Nottingham, Storbritannien.Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - CONF
T1 - Bird species categorization using pose normalized deep convolutional nets
AU - Branson, Steve
AU - Van Horn, Grant
AU - Belongie, Serge
AU - Perona, Pietro
N1 - Publisher Copyright: © 2014. The copyright of this document resides with its authors.
PY - 2014
Y1 - 2014
N2 - 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 [17, 22, 26, 28] 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%).
AB - 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 [17, 22, 26, 28] 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%).
UR - http://www.scopus.com/inward/record.url?scp=84919741208&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:84919741208
T2 - 25th British Machine Vision Conference, BMVC 2014
Y2 - 1 September 2014 through 5 September 2014
ER -
ID: 302044083