articleJan 1, 2017GOLD OA

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

JZJieyu ZhaoTWTianlu WangMYMark YatskarVOVicente OrdóñezKCKai-Wei Chang

University of Virginia · University of Washington

Indexed incrossref

Abstract

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.

Citation impact

770
total citations
FWCI
22.73
Percentile
100%
References
33
Citations per year

Authors

5

Topics & keywords

Topics
Keywords
  • Computer science
  • Inference
  • Task (project management)
  • Artificial intelligence
  • Set (abstract data type)
  • Natural language processing
  • Machine learning
  • Encoding (memory)
UN Sustainable Development Goals
  • Gender equality
No related works found for this paper.

Funding