Err on the Side of Texture: Texture Bias on Real Data
Journal:
arXiv
Published Date:
Dec 13, 2024
Abstract
Bias significantly undermines both the accuracy and trustworthiness of
machine learning models. To date, one of the strongest biases observed in image
classification models is texture bias-where models overly rely on texture
information rather than shape information. Yet, existing approaches for
measuring and mitigating texture bias have not been able to capture how
textures impact model robustness in real-world settings. In this work, we
introduce the Texture Association Value (TAV), a novel metric that quantifies
how strongly models rely on the presence of specific textures when classifying
objects. Leveraging TAV, we demonstrate that model accuracy and robustness are
heavily influenced by texture. Our results show that texture bias explains the
existence of natural adversarial examples, where over 90% of these samples
contain textures that are misaligned with the learned texture of their true
label, resulting in confident mispredictions.