Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang

EMNLP 2017



Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occuring labels and visual input but risk inadvertently encoding social biases found in web corpora.
In this work, we study data and models associated with multilabel object classification and visual semantic role labeling. We find that (a) datasets for these tasks contain significant gender bias and (b) models trained on these datasets further amplify existing bias. For example, the activity cooking is over 33% more likely to involve females than males in a training set, but a trained model amplifies the disparity to 68% at test time. We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for the resulting inference problems. Our method results in no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 33.3% and 44.9% for multilabel classification and visual semantic role labeling, respectively.


  • This paper won the Best Long Paper Award at EMNLP 2017.

Bib entry

author = {Jieyu Zhao and Tianlu Wang and Mark Yatskar and Vicente Ordonez and Kai-Wei Chang},
title = {Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints},
booktitle = {EMNLP},
year = {2017},