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. [...] 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
Supplemental Presentations
Figures and Topics from this paper
Figures
Paper Mentions
Blog Post
291 Citations
Women also Snowboard: Overcoming Bias in Captioning Models
- Computer Science
- ECCV
- 2018
- 134
- Highly Influenced
- PDF
Identifying and Reducing Gender Bias in Word-Level Language Models
- Computer Science
- NAACL-HLT
- 2019
- 34
- Highly Influenced
- PDF
Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models
- Computer Science
- ArXiv
- 2019
- 5
- PDF
Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
- Computer Science
- ACL
- 2020
- 9
- PDF
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
- Computer Science, Mathematics
- ACL
- 2020
- 5
- PDF
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 12
- Highly Influenced
- PDF
How Do We Talk about Other People? Group (Un)Fairness in Natural Language Image Descriptions
- Computer Science
- AAAI 2019
- 2019
- 3
- PDF
References
SHOWING 1-10 OF 41 REFERENCES
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Computer Science, Mathematics
- NIPS
- 2016
- 948
- PDF
Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 114
- PDF
Semantics derived automatically from language corpora necessarily contain human biases
- Computer Science
- ArXiv
- 2016
- 78
- PDF
Show and tell: A neural image caption generator
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 3,649
- PDF
Semantics derived automatically from language corpora contain human-like biases
- Computer Science, Medicine
- Science
- 2017
- 766
- PDF
Commonly Uncommon: Semantic Sparsity in Situation Recognition
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 22
- PDF
Situation Recognition: Visual Semantic Role Labeling for Image Understanding
- Computer Science
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2016
- 129
- PDF
Tractable Semi-supervised Learning of Complex Structured Prediction Models
- Mathematics, Computer Science
- ECML/PKDD
- 2013
- 9
- PDF
Constrained Semi-supervised Learning in the Presence of Unanticipated Classes
- Computer Science
- SIGF
- 2016
- 2
- PDF
VQA: Visual Question Answering
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 2,011
- PDF