Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search

Jialu Wang, Yang Liu, Xin Wang


Abstract
Internet search affects people’s cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image search in this work: the search images are often gender-imbalanced for gender-neutral natural language queries. We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pre-trained on massive image and text data across the internet. Both models suffer from severe gender bias. Therefore, we introduce two novel debiasing approaches: an in-processing fair sampling method to address the gender imbalance issue for training models, and a post-processing feature clipping method base on mutual information to debias multimodal representations of pre-trained models. Extensive experiments on MS-COCO and Flickr30K benchmarks show that our methods significantly reduce the gender bias in image search models.
Anthology ID:
2021.emnlp-main.151
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1995–2008
Language:
URL:
https://aclanthology.org/2021.emnlp-main.151
DOI:
10.18653/v1/2021.emnlp-main.151
Bibkey:
Cite (ACL):
Jialu Wang, Yang Liu, and Xin Wang. 2021. Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1995–2008, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search (Wang et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.151.pdf
Software:
 2021.emnlp-main.151.Software.zip
Video:
 https://aclanthology.org/2021.emnlp-main.151.mp4
Code
 kuanghuei/SCAN +  additional community code
Data
Flickr30kMS COCO