Contrastive Examples for Addressing the Tyranny of the Majority
@article{Sharmanska2020ContrastiveEF, title={Contrastive Examples for Addressing the Tyranny of the Majority}, author={V. Sharmanska and Lisa Anne Hendricks and Trevor Darrell and Novi Quadrianto}, journal={ArXiv}, year={2020}, volume={abs/2004.06524} }
Computer vision algorithms, e.g. for face recognition, favour groups of individuals that are better represented in the training data. This happens because of the generalization that classifiers have to make. It is simpler to fit the majority groups as this fit is more important to overall error. We propose to create a balanced training dataset, consisting of the original dataset plus new data points in which the group memberships are intervened, minorities become majorities and vice versa. We… Expand
Figures, Tables, and Topics from this paper
2 Citations
Fair Attribute Classification through Latent Space De-biasing
- Computer Science
- ArXiv
- 2020
- 1
- Highly Influenced
- PDF
Causal Datasheet for Datasets: An Evaluation Guide for Real-World Data Analysis and Data Collection Design Using Bayesian Networks
- Frontiers in Artificial Intelligence
- 2021
References
SHOWING 1-10 OF 55 REFERENCES
Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings
- Computer Science
- ECCV Workshops
- 2018
- 79
- PDF
Discovering Fair Representations in the Data Domain
- Computer Science
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2019
- 26
- PDF
Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network
- Computer Science
- 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
- 2019
- 59
- Highly Influential
- PDF
Mitigating Unwanted Biases with Adversarial Learning
- Computer Science, Mathematics
- AIES
- 2018
- 310
- Highly Influential
- PDF
Age Progression/Regression by Conditional Adversarial Autoencoder
- Computer Science, Mathematics
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 387
- Highly Influential
- PDF
Learning from Simulated and Unsupervised Images through Adversarial Training
- Computer Science
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2017
- 1,160
- Highly Influential
- PDF
VGGFace2: A Dataset for Recognising Faces across Pose and Age
- Computer Science
- 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018)
- 2018
- 906
- Highly Influential
- PDF
Controllable Invariance through Adversarial Feature Learning
- Computer Science, Mathematics
- NIPS
- 2017
- 121
- Highly Influential
- PDF