Leveraging Gaussian Process Approximations for Rapid Image Overlay Production

Michael Burke

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

Abstract / Description of output

Machine learning models trained using images can be used to generate image overlays by investigating which image areas contribute the most towards model outputs. A common approach used to accomplish this relies on blanking image regions using a sliding window and evaluating the change in model output. Unfortunately,this can be computationally expensive,as it requires numerous model evaluations. This paper shows that a Gaussian process approximation to this blanking approach produces outputs of similar quality,despite requiring significantly fewer model evaluations. This process is illustrated using a user-driven saliency generation problem. Here,pairwise image interest comparisons are used to infer underlying image interest and a Gaussian process model trained to predict the interest value of an image using image features extracted by a convolutional neural network. Interest overlays are generated by evaluating model change at blanking image regions selected using the prediction uncertainty of a Gaussian process regressor.
Original languageEnglish
Title of host publicationProceedings of the ACM Multimedia 2017 Workshop on South African Academic Participation
Place of PublicationMountain View, California, USA
PublisherACM
Pages21-26
Number of pages6
ISBN (Print)978-1-4503-5505-6
DOIs
Publication statusPublished - 23 Oct 2017
EventACM Multimedia 2017 Workshop on South African Academic Participation - Mountain View, United States
Duration: 23 Oct 201723 Oct 2017
http://www.acmmm.org/2017/

Conference

ConferenceACM Multimedia 2017 Workshop on South African Academic Participation
Abbreviated titleSAWACMMM'17
Country/TerritoryUnited States
CityMountain View
Period23/10/1723/10/17
Internet address

Fingerprint

Dive into the research topics of 'Leveraging Gaussian Process Approximations for Rapid Image Overlay Production'. Together they form a unique fingerprint.

Cite this