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}
}
  • Jieyu Zhao, Tianlu Wang, +2 authors Kai-Wei Chang
  • Published in EMNLP 2017
  • Computer Science, Mathematics
  • 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
    276 Citations
    Women also Snowboard: Overcoming Bias in Captioning Models
    • 118
    • Highly Influenced
    • PDF
    Identifying and Reducing Gender Bias in Word-Level Language Models
    • 30
    • Highly Influenced
    • PDF
    Mitigating Gender Bias in Captioning Systems
    Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
    • 5
    • PDF
    Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
    • 7
    • Highly Influenced
    • PDF
    Quantifying Social Biases in Contextual Word Representations
    • 7

    References

    SHOWING 1-10 OF 41 REFERENCES
    Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
    • 111
    • PDF
    Semantics derived automatically from language corpora necessarily contain human biases
    • 73
    • PDF
    Show and tell: A neural image caption generator
    • 3,520
    • PDF
    Semantics derived automatically from language corpora contain human-like biases
    • 703
    • PDF
    Commonly Uncommon: Semantic Sparsity in Situation Recognition
    • 21
    • PDF
    Situation Recognition: Visual Semantic Role Labeling for Image Understanding
    • 125
    • PDF
    Tractable Semi-supervised Learning of Complex Structured Prediction Models
    • 9
    • PDF
    Constrained Semi-supervised Learning in the Presence of Unanticipated Classes
    • 2
    • PDF
    VQA: Visual Question Answering
    • 1,908
    • PDF