Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition
This addresses bias and privacy issues in face recognition systems, which is an incremental improvement for mitigating gender disparities in AI applications.
The paper tackled the problem of gender bias and privacy leakage in face recognition by proposing AGENDA, an adversarial de-biasing algorithm that significantly reduces gender predictability in face descriptors while maintaining reasonable recognition performance.
State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to identifying faces. However, the implicit encoding of gender information in face descriptors has two major issues: (a.) It makes the descriptors susceptible to privacy leakage, i.e. a malicious agent can be trained to predict the face gender from such descriptors. (b.) It appears to contribute to gender bias in face recognition, i.e. we find a significant difference in the recognition accuracy of DCNNs on male and female faces. Therefore, we present a novel `Adversarial Gender De-biasing algorithm (AGENDA)' to reduce the gender information present in face descriptors obtained from previously trained face recognition networks. We show that AGENDA significantly reduces gender predictability of face descriptors. Consequently, we are also able to reduce gender bias in face verification while maintaining reasonable recognition performance.