Bird Species Categorization Using Pose Normalized Deep Convolutional Nets
This work addresses the problem of bird species recognition for computer vision applications, representing an incremental advancement with strong specific gains.
The paper tackles fine-grained visual categorization of bird species by proposing an architecture that integrates pose-normalized deep convolutional features with unaligned image features, achieving a large improvement in classification rates to 75% compared to previous methods' 55-65%.
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%).