SELF-PACED CURRICULUM LEARNING FOR VISUAL QUESTION ANSWERING ON REMOTE SENSING DATA

Zhenghang Yuan, Lichao Mou, Xiao Xiang Zhu

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

8 Scopus citations

Abstract

Answering questions with natural language by extracting information from image has great potential in various applications. Although visual question answering (VQA) for natural image has been broadly studied, VQA for remote sensing data is still in the early research stage. For the same remote sensing image, there exist questions with dramatically different difficulty-levels. Treating these questions equally may mislead the model and limit the VQA model performance. Considering this problem, in this work, we propose a self-paced curriculum learning (SPCL) based VQA model with hard and soft weighting strategies for remote sensing data. Like human learning process, the model is trained from easy to hard question samples gradually. Extensive experimental results on two datasets demonstrate that the proposed training method can achieve promising performance.

Original languageEnglish
Title of host publicationIGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2999-3002
Number of pages4
ISBN (Electronic)9781665403696
DOIs
StatePublished - 2021
Event2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium
Duration: 12 Jul 202116 Jul 2021

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2021-July

Conference

Conference2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/TerritoryBelgium
CityBrussels
Period12/07/2116/07/21

Keywords

  • Deep learning
  • Remote sensing
  • Self-paced curriculum learning (SPCL)
  • Visual question answering (VQA)

Fingerprint

Dive into the research topics of 'SELF-PACED CURRICULUM LEARNING FOR VISUAL QUESTION ANSWERING ON REMOTE SENSING DATA'. Together they form a unique fingerprint.

Cite this