2022 Fiscal Year Research-status Report
Societal biases in vision and language applications
| Project/Area Number |
22K12091
|
|---|
| Research Institution | Osaka 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
|
| Keywords | bias 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.
|
