Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network
This addresses fairness issues in visual datasets for real-world applications, but it is incremental as it builds on existing Bayesian approaches.
The paper tackled the problem of dataset bias and spurious correlations in deep neural networks by proposing an implicit mitigation method using a Bayesian neural network with posterior estimate sharpening, resulting in performance comparable to prior methods on three benchmark datasets.
The fairness of a deep neural network is strongly affected by dataset bias and spurious correlations, both of which are usually present in modern feature-rich and complex visual datasets. Due to the difficulty and variability of the task, no single de-biasing method has been universally successful. In particular, implicit methods not requiring explicit knowledge of bias variables are especially relevant for real-world applications. We propose a novel implicit mitigation method using a Bayesian neural network, allowing us to leverage the relationship between epistemic uncertainties and the presence of bias or spurious correlations in a sample. Our proposed posterior estimate sharpening procedure encourages the network to focus on core features that do not contribute to high uncertainties. Experimental results on three benchmark datasets demonstrate that Bayesian networks with sharpened posterior estimates perform comparably to prior existing methods and show potential worthy of further exploration.