Quantifying Societal Bias Amplification in Image Captioning

We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 13440 - 13449
Main Authors: Hirota, Yusuke, Nakashima, Yuta, Garcia, Noa
Format: Conference Proceeding
Language:English
Japanese
Published: IEEE 01.06.2022
Subjects:
accountability
Computational modeling
Computer vision
Equalizers
fairness
Focusing
Measurement
Predictive models
privacy and ethics in vision; Vision + language
Skin
Transparency
ISSN:1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We study societal bias amplification in image captioning. Image captioning models have been shown to perpetuate gender and racial biases, however, metrics to measure, quantify, and evaluate the societal bias in captions are not yet standardized. We provide a comprehensive study on the strengths and limitations of each metric, and propose LIC, a metric to study captioning bias amplification. We argue that, for image captioning, it is not enough to focus on the correct prediction of the protected attribute, and the whole context should be taken into account. We conduct extensive evaluation on traditional and state-of-the-art image captioning models, and surprisingly find that, by only focusing on the protected attribute prediction, bias mitigation models are unexpectedly amplifying bias.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.01309