DeepVQ: A deep network architecture for vector quantization

Dang-Khoa Le Tan, Huu Le, Tuan Hoang, Thanh-Toan Do, Ngai-Man Cheung

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

10 Citations (Scopus)

Abstract

Vector quantization (VQ) is a classic problem in signal processing, source coding and information theory. Leveraging recent advances in deep neural networks (DNN), this paper bridges the gap between a classic quantization problem and DNN. We introduce - for the first time - a deep network architecture for vector quantization (DeepVQ). Applying recent binary optimization theory, we propose a training algorithm to tackle binary constraints. Notably, our network outputs binary codes directly. As a result, DeepVQ can perform quantization of vectors with a simple forward pass, and this overcomes the exponential complexity issue of previous VQ approaches. Experiments show that our network is able to achieve encouraging results and outperforms recent deep learning-based clustering approaches that have been modified for VQ. Importantly, our network serves as a generic framework which can be applied for other networks in which binary constraints are required.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Subtitle of host publicationCVPRW 2018
EditorsDavid Forsyth, Ivan Laptev, Deva Ramanan, Aude Oliva
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages2579-2582
Number of pages4
ISBN (Electronic)9781538661000
Publication statusPublished - 2018
Externally publishedYes
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2018 - Salt Lake City, United States of America
Duration: 18 Jun 201822 Jun 2018
Conference number: 31st
https://ieeexplore.ieee.org/xpl/conhome/8575058/proceeding (Proceedings)
https://cvpr2018.thecvf.com/program/workshops (Website)

Conference

ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops 2018
Abbreviated titleCVPRW 2018
Country/TerritoryUnited States of America
CitySalt Lake City
Period18/06/1822/06/18
Internet address

Cite this