Simultaneous compression and quantization: A joint approach for efficient unsupervised hashing
Artikel i vetenskaplig tidskrift, 2020

For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization loss. A well-established hashing approach is Iterative Quantization (ITQ), which addresses these two requirements in separate steps. In this paper, we revisit the ITQ approach and propose novel formulations and algorithms to the problem. Specifically, we propose a novel approach, named Simultaneous Compression and Quantization (SCQ), to jointly learn to compress (reduce dimensionality) and binarize input data in a single formulation under strict orthogonal constraint. With this approach, we introduce a loss function and its relaxed version, termed Orthonormal Encoder (OnE) and Orthogonal Encoder (OgE) respectively, which involve challenging binary and orthogonal constraints. We propose to attack the optimization using novel algorithms based on recent advance in cyclic coordinate descent approach. Comprehensive experiments on unsupervised image retrieval demonstrate that our proposed methods consistently outperform other state-of-the-art hashing methods. Notably, our proposed methods outperform recent deep neural networks and GAN based hashing in accuracy, while being very computationally-efficient.


Tuan Hoang

Singapore University of Technology and Design

Thanh Toan Do

University of Liverpool

Huu Le

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Dang Khoa Le-Tan

Singapore University of Technology and Design

Ngai Man Cheung

Singapore University of Technology and Design

Computer Vision and Image Understanding

1077-3142 (ISSN) 1090-235X (eISSN)

Vol. 191 102852



Datavetenskap (datalogi)

Datorseende och robotik (autonoma system)



Mer information

Senast uppdaterat