Traversing latent space using decision ferns

Yan Zuo, Gil Avraham, Tom Drummond

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years. Recently, rapid progress in deep neural networks has given both researchers and practitioners enhanced methods that increase the richness of feature representations, be it from images, text or speech. In this work we show how a constructed latent space can be explored in a controlled manner and argue that this complements well founded inference methods. For constructing the latent space a Variational Autoencoder is used. We present a novel controller module that allows for smooth traversal in the latent space and construct an end-to-end trainable framework. We explore the applicability of our method for performing spatial transformations as well as kinematics for predicting future latent vectors of a video sequence.

Original languageEnglish
Title of host publicationComputer Vision – ACCV 2018
Subtitle of host publication14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I
EditorsC.V. Jawahar, Hongdong Li, Greg Mori, Konrad Schindler
Place of PublicationCham Switzerland
PublisherSpringer
Pages593-608
Number of pages16
ISBN (Electronic)9783030208875
ISBN (Print)9783030208868
DOIs
Publication statusPublished - 2019
EventAsian Conference on Computer Vision 2018 - Perth, Australia
Duration: 2 Dec 20186 Dec 2018
Conference number: 14th
https://link-springer-com.ezproxy.lib.monash.edu.au/book/10.1007/978-3-030-20873-8

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11361
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceAsian Conference on Computer Vision 2018
Abbreviated titleACCV 2018
CountryAustralia
CityPerth
Period2/12/186/12/18
Internet address

Cite this

Zuo, Y., Avraham, G., & Drummond, T. (2019). Traversing latent space using decision ferns. In C. V. Jawahar, H. Li, G. Mori, & K. Schindler (Eds.), Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I (pp. 593-608). (Lecture Notes in Computer Science; Vol. 11361). Cham Switzerland: Springer. https://doi.org/10.1007/978-3-030-20887-5_37
Zuo, Yan ; Avraham, Gil ; Drummond, Tom. / Traversing latent space using decision ferns. Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I. editor / C.V. Jawahar ; Hongdong Li ; Greg Mori ; Konrad Schindler. Cham Switzerland : Springer, 2019. pp. 593-608 (Lecture Notes in Computer Science).
@inproceedings{3d4a3c3750494aa2a7087563cfe05f17,
title = "Traversing latent space using decision ferns",
abstract = "The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years. Recently, rapid progress in deep neural networks has given both researchers and practitioners enhanced methods that increase the richness of feature representations, be it from images, text or speech. In this work we show how a constructed latent space can be explored in a controlled manner and argue that this complements well founded inference methods. For constructing the latent space a Variational Autoencoder is used. We present a novel controller module that allows for smooth traversal in the latent space and construct an end-to-end trainable framework. We explore the applicability of our method for performing spatial transformations as well as kinematics for predicting future latent vectors of a video sequence.",
author = "Yan Zuo and Gil Avraham and Tom Drummond",
year = "2019",
doi = "10.1007/978-3-030-20887-5_37",
language = "English",
isbn = "9783030208868",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "593--608",
editor = "C.V. Jawahar and Hongdong Li and Greg Mori and Konrad Schindler",
booktitle = "Computer Vision – ACCV 2018",

}

Zuo, Y, Avraham, G & Drummond, T 2019, Traversing latent space using decision ferns. in CV Jawahar, H Li, G Mori & K Schindler (eds), Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I. Lecture Notes in Computer Science, vol. 11361, Springer, Cham Switzerland, pp. 593-608, Asian Conference on Computer Vision 2018, Perth, Australia, 2/12/18. https://doi.org/10.1007/978-3-030-20887-5_37

Traversing latent space using decision ferns. / Zuo, Yan; Avraham, Gil; Drummond, Tom.

Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I. ed. / C.V. Jawahar; Hongdong Li; Greg Mori; Konrad Schindler. Cham Switzerland : Springer, 2019. p. 593-608 (Lecture Notes in Computer Science; Vol. 11361).

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - Traversing latent space using decision ferns

AU - Zuo, Yan

AU - Avraham, Gil

AU - Drummond, Tom

PY - 2019

Y1 - 2019

N2 - The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years. Recently, rapid progress in deep neural networks has given both researchers and practitioners enhanced methods that increase the richness of feature representations, be it from images, text or speech. In this work we show how a constructed latent space can be explored in a controlled manner and argue that this complements well founded inference methods. For constructing the latent space a Variational Autoencoder is used. We present a novel controller module that allows for smooth traversal in the latent space and construct an end-to-end trainable framework. We explore the applicability of our method for performing spatial transformations as well as kinematics for predicting future latent vectors of a video sequence.

AB - The practice of transforming raw data to a feature space so that inference can be performed in that space has been popular for many years. Recently, rapid progress in deep neural networks has given both researchers and practitioners enhanced methods that increase the richness of feature representations, be it from images, text or speech. In this work we show how a constructed latent space can be explored in a controlled manner and argue that this complements well founded inference methods. For constructing the latent space a Variational Autoencoder is used. We present a novel controller module that allows for smooth traversal in the latent space and construct an end-to-end trainable framework. We explore the applicability of our method for performing spatial transformations as well as kinematics for predicting future latent vectors of a video sequence.

UR - http://www.scopus.com/inward/record.url?scp=85066786728&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-20887-5_37

DO - 10.1007/978-3-030-20887-5_37

M3 - Conference Paper

AN - SCOPUS:85066786728

SN - 9783030208868

T3 - Lecture Notes in Computer Science

SP - 593

EP - 608

BT - Computer Vision – ACCV 2018

A2 - Jawahar, C.V.

A2 - Li, Hongdong

A2 - Mori, Greg

A2 - Schindler, Konrad

PB - Springer

CY - Cham Switzerland

ER -

Zuo Y, Avraham G, Drummond T. Traversing latent space using decision ferns. In Jawahar CV, Li H, Mori G, Schindler K, editors, Computer Vision – ACCV 2018: 14th Asian Conference on Computer Vision Perth, Australia, December 2–6, 2018 Revised Selected Papers, Part I. Cham Switzerland: Springer. 2019. p. 593-608. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-030-20887-5_37