Distribution Entropy Boosted VLAD for Image Retrieval
1
State Key Laboratory of Automotive Simulation and Control, Jilin University, Changchun 130022, China
2
College of Communication Engineering, Jilin University, Changchun 130012, China
3
College of Instrumentation and Electrical Engineering, Jilin University, Changchun 130061, China
4
College of Computer Science and Technology, Jilin University, Changchun 130012, China
5
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun 130012, China
6
School of Mechanical Science and Engineering, Jilin University, Changchun 130025, China
*
Author to whom correspondence should be addressed.
Academic Editors: Andreas Holzinger, Adom Giffin and Kevin H. Knuth
Entropy 2016, 18(8), 311; https://doi.org/10.3390/e18080311
Received: 26 February 2016 / Revised: 12 July 2016 / Accepted: 16 August 2016 / Published: 24 August 2016
(This article belongs to the Special Issue Machine Learning and Entropy: Discover Unknown Unknowns in Complex Data Sets)
Several recent works have shown that aggregating local descriptors to generate global image representation results in great efficiency for retrieval and classification tasks. The most popular method following this approach is VLAD (Vector of Locally Aggregated Descriptors). We present a novel image presentation called Distribution Entropy Boosted VLAD (EVLAD), which extends the original vector of locally aggregated descriptors. The original VLAD adopts only residuals to depict the distribution information of every visual word and neglects other statistical clues, so its discriminative power is limited. To address this issue, this paper proposes the use of the distribution entropy of each cluster as supplementary information to enhance the search accuracy. To fuse two feature sources organically, two fusion methods after a new normalization stage meeting power law are also investigated, which generate identically sized and double-sized vectors as the original VLAD. We validate our approach in image retrieval and image classification experiments. Experimental results demonstrate the effectiveness of our algorithm.
View Full-Text
Keywords:
image retrieval; VLAD; distribution entropy; quantization error; normalization
▼
Show Figures
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Zhou, Q.; Wang, C.; Liu, P.; Li, Q.; Wang, Y.; Chen, S. Distribution Entropy Boosted VLAD for Image Retrieval. Entropy 2016, 18, 311. https://doi.org/10.3390/e18080311
AMA Style
Zhou Q, Wang C, Liu P, Li Q, Wang Y, Chen S. Distribution Entropy Boosted VLAD for Image Retrieval. Entropy. 2016; 18(8):311. https://doi.org/10.3390/e18080311
Chicago/Turabian StyleZhou, Qiuzhan; Wang, Cheng; Liu, Pingping; Li, Qingliang; Wang, Yeran; Chen, Shuozhang. 2016. "Distribution Entropy Boosted VLAD for Image Retrieval" Entropy 18, no. 8: 311. https://doi.org/10.3390/e18080311
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
Search more from Scilit