%0 Conference Paper %B Computer Vision (ICCV), 2011 IEEE International Conference on %D 2011 %T Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance %A Farrell,R. %A Oza,O. %A Zhang,Ning %A Morariu,V.I. %A Darrell,T. %A Davis, Larry S. %K appearance %K Birdlets;category %K categorization;subordinate-level %K detection;pose %K detectors;pose-normalized %K distinctions;shape %K estimation; %K extraction;pose %K extraction;subordinate-level %K information %K model;salient %K models;volumetric %K pixels;part %K poselet %K primitives;computer %K resolution;information %K retrieval;object %K scheme;volumetric %K taxonomy;computer %K vision;image %X Subordinate-level categorization typically rests on establishing salient distinctions between part-level characteristics of objects, in contrast to basic-level categorization, where the presence or absence of parts is determinative. We develop an approach for subordinate categorization in vision, focusing on an avian domain due to the fine-grained structure of the category taxonomy for this domain. We explore a pose-normalized appearance model based on a volumetric poselet scheme. The variation in shape and appearance properties of these parts across a taxonomy provides the cues needed for subordinate categorization. Training pose detectors requires a relatively large amount of training data per category when done from scratch; using a subordinate-level approach, we exploit a pose classifier trained at the basic-level, and extract part appearance and shape information to build subordinate-level models. Our model associates the underlying image pattern parameters used for detection with corresponding volumetric part location, scale and orientation parameters. These parameters implicitly define a mapping from the image pixels into a pose-normalized appearance space, removing view and pose dependencies, facilitating fine-grained categorization from relatively few training examples. %B Computer Vision (ICCV), 2011 IEEE International Conference on %P 161 - 168 %8 2011/11// %G eng %R 10.1109/ICCV.2011.6126238