Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

@inproceedings{Zhao2017MenAL,
  title={Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints},
  author={Jieyu Zhao and Tianlu Wang and Mark Yatskar and Vicente Ordonez and Kai-Wei Chang},
  booktitle={EMNLP},
  year={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-occurring 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… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification and visual semantic role labeling, respectively.

Citations

Publications citing this paper.
SHOWING 1-10 OF 69 CITATIONS, ESTIMATED 39% COVERAGE

Testing Deep Neural Network based Image Classifiers

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Feature-Wise Bias Amplification

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function

Yusu Qian, Urwa Muaz, Ben Zhang, Jae Won Hyun
  • ArXiv
  • 2019
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Visual semantic role labeling requires recognizing activities and semantic context in images

  • 2019
VIEW 8 EXCERPTS
CITES RESULTS & BACKGROUND
HIGHLY INFLUENCED

Attenuating Bias in Word vectors

VIEW 1 EXCERPT
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2017
2019

CITATION STATISTICS

  • 8 Highly Influenced Citations

  • Averaged 27 Citations per year over the last 3 years

  • 85% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 31 REFERENCES

Situation Recognition: Visual Semantic Role Labeling for Image Understanding

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Commonly Uncommon: Semantic Sparsity in Situation Recognition

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…