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

@article{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},
  journal={ArXiv},
  year={2017},
  volume={abs/1707.09457}
}
  • Jieyu Zhao, Tianlu Wang, +2 authors Kai-Wei Chang
  • Published 2017
  • Computer Science, Mathematics
  • ArXiv
  • Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. [...] Key Method We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. 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…Expand Abstract
    Directing Generative Networks with Weighted Maximum Mean Discrepancy
    Social Informatics
    What Is Artificial Intelligence
    Experimental analysis of representation learning systems
    Visual semantic role labeling requires recognizing activities and semantic context in images
    Ju n 20 19 Measuring Bias in Contextualized Word Representations Keita

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 41 REFERENCES
    Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
    • 104
    • Open Access
    Semantics derived automatically from language corpora necessarily contain human biases
    • 73
    • Open Access
    Show and tell: A neural image caption generator
    • 3,388
    • Open Access
    Semantics derived automatically from language corpora contain human-like biases
    • 613
    • Open Access
    Commonly Uncommon: Semantic Sparsity in Situation Recognition
    • 21
    • Open Access
    Situation Recognition: Visual Semantic Role Labeling for Image Understanding
    • 119
    • Open Access
    Tractable Semi-supervised Learning of Complex Structured Prediction Models
    • 9
    • Open Access
    Constrained Semi-supervised Learning in the Presence of Unanticipated Classes
    • 2
    • Open Access
    VQA: Visual Question Answering
    • 1,818
    • Open Access