FhVLAD: Fine-grained quantization and encoding high-order descriptor statistics for scalable image retrieval

We are interested in the encoding of local descriptors of an image ( e.g. SIFT) to design a compact representation vector and thereby address scalable image retrieval. We revisit the implicit design choices in the popular vector of locally aggregated descriptors (VLAD), which aggregates the residual...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Multimedia tools and applications Ročník 80; číslo 28-29; s. 35495 - 35520
Hlavní autori: Bhowmick, Alexy, Saharia, Sarat, Hazarika, Shyamanta M.
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.11.2021
Springer Nature B.V
Predmet:
1166: Advances of machine learning in data analytics and visual information processing
Computer Communication Networks
Computer Science
Data Structures and Information Theory
Image management
Image retrieval
Measurement
Multimedia Information Systems
Special Purpose and Application-Based Systems
Statistics
VLAD
Fine-grained
Residual
High-order
Image retrieval
ISSN:1380-7501, 1573-7721
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:We are interested in the encoding of local descriptors of an image ( e.g. SIFT) to design a compact representation vector and thereby address scalable image retrieval. We revisit the implicit design choices in the popular vector of locally aggregated descriptors (VLAD), which aggregates the residuals of descriptors to the codewords. VLAD’s use of a coarse codebook and first-order descriptor statistics in residual computation results in less discriminative residuals. To address this problem, we propose a division of codebook feature space using a novel fine-grained quantization strategy. After quantization, we embed the resulting residuals with high-order statistics of descriptor distribution. Experiments on three challenging image retrieval datasets (INRIA Holidays, UKBench, Oxford 5k) confirm the improved discriminative power of our novel encoding method called FhVLAD. We observe superior accuracy to baseline and competitive performance to state-of-the-art techniques with a limited increase in dimension.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-020-10491-7