Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
Authors:
Preprint
Abstract
Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity recognition or image captioning. Various mitigation techniques have been presented to prevent models from utilizing or learning such biases. However, there has been little systematic comparison between these techniques. We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation. Using this benchmark, we provide a thorough analysis of a wide range of techniques. We highlight the shortcomings of popular adversarial training approaches for bias mitigation, propose a simple but similarly effective alternative to the inference-time Reducing Bias Amplification method of Zhao et al., and design a domain-independent training technique that outperforms all other methods. Finally, we validate our findings on the attribute classification task in the CelebA dataset, where attribute presence is known to be correlated with the gender of people in the image, and demonstrate that the proposed technique is effective at mitigating real-world gender bias.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Discovering Fair Representations in the Data Domain2019
- REPAIR: Removing Representation Bias by Dataset Resampling2019
- Learning Not to Learn: Training Deep Neural Networks With Biased Data2019
- Class-Balanced Loss Based on Effective Number of Samples2019
- Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings2019
- A systematic study of the class imbalance problem in convolutional neural networksNeural Networks, 2018
- Deep Residual Learning for Image Recognition2016
- Classifier adaptation at prediction time2015
- Diagnosing Error in Object Detectors2012
- Undoing the Damage of Dataset Bias2012