Covering up bias in CelebA-like datasets with Markov blankets: A post-hoc cure for attribute prior avoidance

• DOI: 10.48550/arxiv.1907.12917
• Publication Date: 2019-01-01
• Authors: Prabhu, Vinay Uday; Yap, Dian Ang; Wang, Alexander; Whaley, John
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology; Machine Learning (cs.LG)

Attribute prior avoidance entails subconscious or willful non-modeling of (meta)attributes that datasets are oft born with, such as the 40 semantic facial attributes associated with the CelebA and CelebA-HQ datasets. The consequences of this infirmity, we discover, are especially stark in state-of-the-art deep generative models learned on these datasets that just model the pixel-space measurements, resulting in an inter-attribute bias-laden latent space. This viscerally manifests itself when we perform face manipulation experiments based on latent vector interpolations. In this paper, we address this and propose a post-hoc solution that utilizes an Ising attribute prior learned in the attribute space and showcase its efficacy via qualitative experiments.<br/>Accepted for presentation at the first workshop on Invertible Neural Networks and Normalizing Flows (ICML 2019), Long Beach, CA, USA<br/>