A course-focused dual curriculum for image captioning

Mohammad Alsharid, Rasheed El-Bouri, Harshita Sharma, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble

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

6 Scopus citations

Abstract

We propose a curriculum learning captioning method to caption fetal ultrasound images by training a model to dynamically transition between two different modalities (image and text) as training progresses. Specifically, we propose a course-focused dual curriculum method, where a course is training with a curriculum based on only one of the two modalities involved in image captioning. We compare two configurations of the course-focused dual curriculum; an image-first course-focused dual curriculum which prepares the early training batches primarily on the complexity of the image information before slowly introducing an order of batches for training based on the complexity of the text information, and a text-first course-focused dual curriculum which operates in reverse. The evaluation results show that dynamically transitioning between text and images over epochs of training improves results when compared to the scenario where both modalities are considered in equal measure in every epoch.

Original languageEnglish
Title of host publication2021 IEEE 18th International Symposium on Biomedical Imaging, ISBI 2021
PublisherIEEE Computer Society
Pages716-720
Number of pages5
ISBN (Electronic)9781665412469
DOIs
StatePublished - 13 Apr 2021
Externally publishedYes
Event18th IEEE International Symposium on Biomedical Imaging, ISBI 2021 - Nice, France
Duration: 13 Apr 202116 Apr 2021

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2021-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference18th IEEE International Symposium on Biomedical Imaging, ISBI 2021
Country/TerritoryFrance
CityNice
Period13/04/2116/04/21

Funding

FundersFunder number
EPSRC Industrial Strategy Challenge Fund
Engineering and Physical Sciences Research CouncilEP/MO13774/1
Rhodes Scholarships
NIHR Imperial Biomedical Research Centre
NIHR Oxford Biomedical Research Centre

    Keywords

    • Curriculum learning
    • Fetal ultrasound
    • Image captioning
    • Image description
    • Meta-learning

    Fingerprint

    Dive into the research topics of 'A course-focused dual curriculum for image captioning'. Together they form a unique fingerprint.

    Cite this