A Caltech Library Service

CompactKdt: Compact Signatures for Accurate Large Scale Object Recognition

Aly, Mohamed and Munich, Mario and Perona, Pietro (2012) CompactKdt: Compact Signatures for Accurate Large Scale Object Recognition. In: IEEE Workshop on Applications of Computer Vision 2012. IEEE , pp. 505-512. ISBN 978-1-4673-0232-6.

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


We present a novel algorithm, Compact Kd-Trees (CompactKdt), that achieves state-of-the-art performance in searching large scale object image collections. The algorithm uses an order of magnitude less storage and computations by making use of both the full local features (e.g. SIFT) and their compact binary signatures to build and search the K-Tree. We compare classical PCA dimensionality reduction to three methods for generating compact binary representations for the features: Spectral Hashing, Locality Sensitive Hashing, and Locality Sensitive Binary Codes. CompactKdt achieves significant performance gain over using the binary signatures alone, and comparable performance to using the full features alone. Finally, our experiments show significantly better performance than the state-of-the-art Bag of Words (BoW) methods with equivalent or less storage and computational cost.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Munich, Mario0000-0002-6665-7473
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2012 IEEE. Date of Conference: 9-11 January 2012; Date of Current Version: 5 March 2012; Issue Date: 9-11 January 2012. This research was supported by ONR grant N00173-09-C-4005.
Funding AgencyGrant Number
Office of Naval Research (ONR)N00173-09- C-4005
Record Number:CaltechAUTHORS:20120816-143947173
Persistent URL:
Official Citation:Aly, M.; Munich, M.; Perona, P.; , "CompactKdt: Compact signatures for accurate large scale object recognition," Applications of Computer Vision (WACV), 2012 IEEE Workshop on , vol., no., pp.505-512, 9-11 Jan. 2012 doi: 10.1109/WACV.2012.6162995
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:33276
Deposited By: Jason Perez
Deposited On:16 Aug 2012 23:18
Last Modified:09 Nov 2021 21:33

Repository Staff Only: item control page