DocumentCode :
71883
Title :
Asymmetric Distances for Binary Embeddings
Author :
Gordo, Albert ; Perronnin, Florent ; Yunchao Gong ; Lazebnik, Svetlana
Author_Institution :
LEAR Group, INRIA Grenoble Rhone-Alpes, Montbonnot, France
Volume :
36
Issue :
1
fYear :
2014
fDate :
Jan. 2014
Firstpage :
33
Lastpage :
47
Abstract :
In large-scale query-by-example retrieval, embedding image signatures in a binary space offers two benefits: data compression and search efficiency. While most embedding algorithms binarize both query and database signatures, it has been noted that this is not strictly a requirement. Indeed, asymmetric schemes that binarize the database signatures but not the query still enjoy the same two benefits but may provide superior accuracy. In this work, we propose two general asymmetric distances that are applicable to a wide variety of embedding techniques including locality sensitive hashing (LSH), locality sensitive binary codes (LSBC), spectral hashing (SH), PCA embedding (PCAE), PCAE with random rotations (PCAE-RR), and PCAE with iterative quantization (PCAE-ITQ). We experiment on four public benchmarks containing up to 1M images and show that the proposed asymmetric distances consistently lead to large improvements over the symmetric Hamming distance for all binary embedding techniques.
Keywords :
cryptography; image coding; image retrieval; iterative methods; principal component analysis; LSBC; LSH; PCA embedding; PCAE-ITQ; PCAE-RR; asymmetric distance; asymmetric scheme; binary embedding technique; data compression; database signature; image signature; iterative quantization; locality sensitive binary code; locality sensitive hashing; query-by-example retrieval; random rotation; search efficiency; spectral hashing; symmetric Hamming distance; Algorithm design and analysis; Euclidean distance; Kernel; Matrix decomposition; Principal component analysis; Quantization (signal); Vectors; Large-scale retrieval; asymmetric distances; binary codes;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2013.101
Filename :
6518116
Link To Document :
بازگشت