2015 Data Compression Conference

Optimizing Binary Fisher Codes for Visual Search Zhe Wang, Ling-Yu Duan, Jie Lin, Jie Chen, Tiejun Huang, and Wen Gao The Institute of Digital Media, Peking University, Beijing, China {zhew,lingyu,linjie,cjie,tjhuang,wgao}@pku.edu.cn

Fisher vectors (FV), a global representation obtained by aggregating local invariant features (e.g., SIFT), generates the state-of-the-art descriptor for visual search, due to highly discriminative power and small visual vocabulary. Nevertheless, a highdimensional raw FV can be further compressed to reduce feature storage and improve search efficiency. In this paper, we formulate the FV compression as a resourceconstrained optimization problem. Let A(.) denote search accuracy, R(.) descriptor size, and C(.) compression complexity. Our goal is to design an optimal quantizer q(.) to compress Fisher vector g by maximizing search accuracy A(q(g)) subject to the constraints of descriptor length Rbudget , and computational complexity Cbudget : max A(q(g)) s.t. R(q) ≤ Rbudget q

and C(q) ≤ Cbudget .


Accordingly, we present selective binary Fisher codes (SBFC) to compress the raw FV. Given a raw Fisher vector [X1 , X2 , ..., XM ] with M Guassian functions, where Xi (1 ≤ i ≤ M ) denotes the i-th sub-vector. Firstly, to fulfill the constraint of compression complexity, we binarize the FV by a sign function; accordingly, we get a binarized Fisher code (BFC) B = [B1 , B2 , ..., Bm ], where each binary sub-vector code Bi = sgn(Xi ). Secondly, we propose to select discriminative bits from the binarized FV (BFC) to maximize search performance, subject to the constraint of descriptor length. We introduce two measurements of “local certainty” and “global informativity” to filter in discriminative bits towards high performance and low complexity, as well as sufficient descriptor compactness. In our work, “local certainty” is defined as the variance of each sub-vector Xi of the raw FV, and “global informativity” the bitwise entropy of each dimension in BFC derived from an independent set of training images. By “local certainty”, we filter in part of binary sub-vector codes Bij (1 ≤ j ≤ M  , M  ≤ M ) from BFC B, while by “global informativity”, we further select a subset of bits with high entropy from each binary sub-vector Bij . Extensive experiments over the MPEG Compact Descriptor for Visual Search (CDVS) benchmark datasets have shown that SBFC can achieve a high compression ratio of 128:1 at extremely low complexity of 0.015 MB memory usage and 1 ms (tested on Intel i5 − 3470) with a minor mAP drop of less than 1%. Compared with typical compression schemes such as Product Quantization(PQ) and Hashing algorithms, SBFC may incur much less memory and time cost. Note that PQ often requires tens of sub-codebooks while Hashing algorithms involve thousands of hash functions. In particular, a simplified version of SBFC (by omitting “global informativity”), SCFV, has been adopted by the MPEG CDVS standard. In the CDVS evaluation framework, SCFV has achieved promising performance with the mean Average Precision (mAP) 85% and the success rate of Top Match 91% on average at the memory cost of 40KB. Acknowledgements: This work was supported by the National Natural Science Foundation of China under grants 61271311, 61390515, 61421062. 1068-0314/15 $31.00 © 2015 IEEE DOI 10.1109/DCC.2015.71


Optimizing Binary Fisher Codes for Visual Search - IEEE Xplore

The Institute of Digital Media, Peking University, Beijing, China. {zhew,lingyu,linjie,cjie,tjhuang,wgao}@pku.edu.cn. Fisher vectors (FV), a global representation obtained by aggregating local invari- ant features (e.g., SIFT), generates the state-of-the-art descriptor for visual search, due to highly discriminative power and small ...

102KB Sizes 0 Downloads 253 Views

Recommend Documents

Fountain codes - IEEE Xplore
7 Richardson, T., Shokrollahi, M.A., and Urbanke, R.: 'Design of capacity-approaching irregular low-density parity check codes', IEEE. Trans. Inf. Theory, 2001 ...

Providing Secrecy with Lattice Codes - IEEE Xplore
Wireless Communications and Networking Laboratory. Electrical Engineering Department. The Pennsylvania State University, University Park, PA 16802.

Oriented Modulation for Watermarking in Direct Binary ... - IEEE Xplore
watermark embedding, while maintaining high image quality. This technique is ... extracted features and ultimately to decode the watermark data. Experimental ...

Dynamic Interactions between Visual Experiences ... - IEEE Xplore
Abstract—The primary aim of this special session is to inform the conference's interdisciplinary audience about the state-of-the-art in developmental studies of ...

overlapped quasi-arithmetic codes for distributed video ... - IEEE Xplore
The presence of correlated side information at the decoder is used to remove this ... Index Terms— Distributed video coding, Wyner-Ziv coding, coding with side ...

Delay-Optimal Burst Erasure Codes for Parallel Links - IEEE Xplore
Cisco Systems, 170 West Tasman Drive, San Jose, CA 95134, USA. Email: ∗{leeoz ... implications on the code design – erasure burst and link outage.

A Survey on Network Codes for Distributed Storage - IEEE Xplore
ABSTRACT | Distributed storage systems often introduce redundancy to increase reliability. When coding is used, the repair problem arises: if a node storing ...

Organizing User Search Histories - IEEE Xplore
Dec 21, 2010 - Abstract—Users are increasingly pursuing complex task-oriented goals on the web, such as making travel arrangements, managing finances ...

TechWare: Mobile Media Search Resources - IEEE Xplore
Jun 15, 2011 - es on mobile media search, which has enjoyed rapid ... device for all our social, business, and ..... ing algorithms in Java for data mining tasks.

A Modified Binary Particle Swarm Optimization ... - IEEE Xplore
Aug 22, 2007 - All particles are initialized as random binary vectors, and the Smallest Position. Value (SPV) rule is used to construct a mapping from binary.

Entity Synonyms for Structured Web Search - IEEE Xplore
Abstract—Nowadays, there are many queries issued to search engines targeting at finding values from structured data (e.g., movie showtime of a specific ...

Discrete Binary Cat Swarm Optimization Algorithm - IEEE Xplore
K. N. Toosi university of Tech. ... its best personal experience and the best experience of the .... the cat and the best position found by members of cat swarm.

Generalized quasi-cyclic low-density parity-check codes ... - IEEE Xplore
Email: {sd07501,hmatsui,smita}@toyota-ti.ac.jp. Abstract—In this study, we proved that several promising classes of codes based on finite geometries cannot be ...

performance of random fingerprinting codes under ... - IEEE Xplore
University of Illinois at Urbana-Champaign, USA. ABSTRACT. This paper analyzes the performance of arbitrary nonlinear collu- sion attacks on random fingerprinting codes. We derive the error exponent of the fingerprinting system, which determines the

Performance of Orthogonal Fingerprinting Codes Under ... - IEEE Xplore
Abstract—We study the effect of the noise distribution on the error probability of the detection test when a class of randomly ro- tated spherical fingerprints is used. The detection test is performed by a focused correlation detector, and the sphe

Buffer-Aided Two-Way Relaying with Lattice Codes - IEEE Xplore
relaying with lattice codes to improve the sum-rate in asymmetric SNR two-way relay channels (TWRCs). Specifically, the relay can store some amount of data.

IEEE Photonics Technology - IEEE Xplore
Abstract—Due to the high beam divergence of standard laser diodes (LDs), these are not suitable for wavelength-selective feed- back without extra optical ...

Inferring Users' Image-Search Goals with Pseudo-images - IEEE Xplore
text-based search-goal inference are also big challenges for image-based user .... If we view the original images in the search results as the original samples,.

wright layout - IEEE Xplore
tive specifications for voice over asynchronous transfer mode (VoATM) [2], voice over IP. (VoIP), and voice over frame relay (VoFR) [3]. Much has been written ...

Device Ensembles - IEEE Xplore
Dec 2, 2004 - time, the computer and consumer electronics indus- tries are defining ... tered on data synchronization between desktops and personal digital ...

wright layout - IEEE Xplore
ACCEPTED FROM OPEN CALL. INTRODUCTION. Two trends motivate this article: first, the growth of telecommunications industry interest in the implementation ...

Toward “Pseudo-Haptic Avatars”: Modifying the Visual ... - IEEE Xplore
In our experimental setup, participants could watch their self-avatar in a virtual environment in mirror mode while performing a weight lifting task. Users could ...

Evolutionary Computation, IEEE Transactions on - IEEE Xplore
search strategy to a great number of habitats and prey distributions. We propose to synthesize a similar search strategy for the massively multimodal problems of ...