DocumentCode :
60151
Title :
Looking Inside Category: Subcategory-Aware Object Recognition
Author :
Jian Dong ; Qiang Chen ; Jiashi Feng ; Kui Jia ; Zhongyang Huang ; Shuicheng Yan
Author_Institution :
Dept. of Electr. & Comput. Eng., Nat. Univ. of Singapore, Singapore, Singapore
Volume :
25
Issue :
8
fYear :
2015
fDate :
Aug. 2015
Firstpage :
1322
Lastpage :
1334
Abstract :
In this paper, we present a subcategory-aware recognition framework to boost category level object classification performance. Different from the existing monolithic model approaches, we aim to automatically leverage the embedded subcategory structure to assist the further category level recognition. Motivated by the observation of considerable intra-class diversities and inter-class ambiguities in many current object classification data sets, we explicitly split data into subcategories by ambiguity-guided subcategory mining. The resulting subcategories are seamlessly integrated into the state-of-the-art detection-assisted classification framework. In particular, we build the instance affinity graph by combining both intra-class similarity and inter-class ambiguity. Visual subcategories, which correspond to the dense subgraphs, are detected by the graph shift algorithm. We then train an individual model for each subcategory rather than an attempt to represent an object category with a monolithic model. Related samples, which are informative for subcategory classification, are utilized to regularize each subcategory model. Finally, the responses from subcategory models are aggregated by subcategory-aware kernel regression. The extensive experiments over the PASCAL visual object challenge (VOC) 2007 and PASCAL VOC 2010 databases show the state-of-the-art performance from our framework.
Keywords :
graph theory; image classification; image representation; object detection; object recognition; PASCAL VOC 2007; PASCAL VOC 2010; PASCAL visual object challenge 2007; affinity graph; ambiguity-guided subcategory mining; category level recognition; embedded subcategory structure; graph shift algorithm; monolithic model approach; object category represention; object classification performance; state-of-the-art detection-assisted classification framework; subcategory-aware kernel regression; subcategory-aware object recognition; Data mining; Detectors; Feature extraction; Object detection; Shape; Training; Visualization; Contextualization; object classification; related samples; subcategory mining;
fLanguage :
English
Journal_Title :
Circuits and Systems for Video Technology, IEEE Transactions on
Publisher :
ieee
ISSN :
1051-8215
Type :
jour
DOI :
10.1109/TCSVT.2014.2355697
Filename :
6894209
Link To Document :
بازگشت