• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2022 Fiscal Year Research-status Report

Societal biases in vision and language applications

Research Project

Project/Area Number 22K12091
Research InstitutionOsaka University

Principal Investigator

GARCIA・DOCAMPO NOA  大阪大学, データビリティフロンティア機構, 特任助教(常勤) (80870005)

Project Period (FY) 2022-04-01 – 2026-03-31
Keywordsbias in computer vision / computer vision / image captioning / vision and language / ethical ai
Outline of Annual Research Achievements

In this project, we have investigated the problem of societal bias in image captioning and multimodal vision and language models. As an outcome of the first year of research:
* We have shown that captioning models encode gender and racial bias.
* We have proposed a new metric to measure societal bias.
* We have annotated a dataset to study and mitigate societal bias.
* We have designed a bias mitigation method for image captioning.

Current Status of Research Progress
Current Status of Research Progress

1: Research has progressed more than it was originally planned.

Reason

In the first year, we have achieved more milestones than originally planned, and have published our work on top conferences in the field.

Strategy for Future Research Activity

Next, we will explore societal bias in text-to-image generation models.

Causes of Carryover

Due to COVID-19 travel restrictions, international conferences were held online. Funding for travel will be used in upcoming conferences in the next fiscal year.

  • Research Products

    (5 results)

All 2022

All Presentation (5 results) (of which Int'l Joint Research: 3 results,  Invited: 2 results)

  • [Presentation] Quantifying Societal Bias Amplification in Image Captioning2022

    • Author(s)
      Yusuke Hirota
    • Organizer
      IEEE/CVF Computer Vision and Pattern Recognition 2022
    • Int'l Joint Research
  • [Presentation] Quantifying Societal Bias Amplification in Image Captioning2022

    • Author(s)
      Yusuke Hirota
    • Organizer
      The 25th Meeting on Image Recognition and Understanding
    • Invited
  • [Presentation] Gender and Racial Bias in Visual Question Answering Datasets2022

    • Author(s)
      Yusuke Hirota
    • Organizer
      ACM Conference on Fairness, Accountability, and Transparency 2022
    • Int'l Joint Research
  • [Presentation] Societal biases in vision and language2022

    • Author(s)
      Noa Garcia
    • Organizer
      Czech Technical University in Prague
    • Int'l Joint Research / Invited
  • [Presentation] Uncovering societal bias in modern artificial intelligence models2022

    • Author(s)
      Noa Garcia
    • Organizer
      III ACE Japan Meeting

URL: 

Published: 2023-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi