DocumentCode :
729770
Title :
Learning compact binary codes via pairwise correlation reconstruction
Author :
Xiao-Jiao Mao ; Yu-Bin Yang ; Ning Li
Author_Institution :
State Key Lab. for Novel Software Technol., Nanjing Univ., Nanjing, China
fYear :
2015
fDate :
June 29 2015-July 3 2015
Firstpage :
1
Lastpage :
6
Abstract :
Due to the explosive growth of visual data and the raised urgent needs for more efficient nearest neighbor search methods, hashing methods have been widely studied in recent years. However, parameter optimization of the hash function in most available approaches is tightly coupled with the form of the function itself, which makes the optimization difficult and consequently affects the similarity preserving performance of hashing. To address this issue, we propose a novel pairwise correlation reconstruction framework for learning compact binary codes flexibly. Firstly, each data point is projected into a metric space and represented as a vector encoding the underlying local and global structure of the input space. The similarities of the data are then measured by the pairwise correlations of the learned vectors, which are represented as Euclidean distances. Afterwards, in order to preserve the similarities maximally, the optimal binary codes are learned by reconstructing the pairwise correlations. Experimental results are provided and analyzed on four commonly used benchmark datasets to demonstrate that the proposed method achieves the best nearest neighbor search performance comparing with the state-of-the-art methods.
Keywords :
binary codes; image coding; image reconstruction; learning (artificial intelligence); search problems; Euclidean distances; compact binary codes learning; data point; data similarities; hash function; hashing methods; learned vectors; metric space; nearest neighbor search methods; optimal binary codes; pairwise correlation reconstruction framework; pairwise correlations; parameter optimization; vector encoding; visual data; Binary codes; Dictionaries; Image reconstruction; Measurement; Optimization; Pairwise error probability; Semantics; Binary code learning; pairwise correlation reconstruction; similarity learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2015 IEEE International Conference on
Conference_Location :
Turin
Type :
conf
DOI :
10.1109/ICME.2015.7177488
Filename :
7177488
Link To Document :
بازگشت