Simultaneous feature aggregating and hashing for compact binary code learning
Journal article, 2019

Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, for each image, local descriptors are first aggregated as a global representation vector. This global vector is then subjected to a hashing function to generate a binary hash code. In previous works, the aggregating and the hashing processes are designed independently. Hence, these frameworks may generate suboptimal hash codes. In this paper, we first propose a novel unsupervised hashing framework in which feature aggregating and hashing are designed simultaneously and optimized jointly. Specifically, our joint optimization generates aggregated representations that can be better reconstructed by some binary codes. This leads to more discriminative binary hash codes and improved retrieval accuracy. In addition, the proposed method is flexible. It can be extended for supervised hashing. When the data label is available, the framework can be adapted to learn binary codes which minimize the reconstruction loss with respect to label vectors. Furthermore, we also propose a fast version of the state-of-the-art hashing method Binary Autoencoder to be used in our proposed frameworks. Extensive experiments on benchmark datasets under various settings show that the proposed methods outperform the state-of-the-art unsupervised and supervised hashing methods.

aggregating

embedding

Image search

binary hashing

Author

Thanh Toan Do

University of Liverpool

Khoa Le

Singapore University of Technology and Design

Tuan Hoang

Singapore University of Technology and Design

Huu Le

Chalmers, Electrical Engineering, Signalbehandling och medicinsk teknik, Imaging and Image Analysis

Tam V. Nguyen

University of Dayton

Ngai Man Cheung

Singapore University of Technology and Design

IEEE Transactions on Image Processing

1057-7149 (ISSN)

Vol. 28 10 4954-4969 8709820

Subject Categories

Computer Science

Computer Vision and Robotics (Autonomous Systems)

Medical Image Processing

DOI

10.1109/TIP.2019.2913509

More information

Latest update

11/7/2019