Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Stone, Rebecca S, Ravikumar, Nishant, Bulpitt, Andrew J, Hogg, David C
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911784338718720
author Stone, Rebecca S
Ravikumar, Nishant
Bulpitt, Andrew J
Hogg, David C
author_facet Stone, Rebecca S
Ravikumar, Nishant
Bulpitt, Andrew J
Hogg, David C
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2303_16564
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network
Stone, Rebecca S
Ravikumar, Nishant
Bulpitt, Andrew J
Hogg, David C
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Implicit Visual Bias Mitigation by Posterior Estimate Sharpening of a Bayesian Neural Network
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2303.16564