Err on the Side of Texture: Texture Bias on Real Data

December 13, 2024 Β· Declared Dead Β· πŸ› 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Blaine Hoak, Ryan Sheatsley, Patrick McDaniel arXiv ID 2412.10597 Category cs.CV: Computer Vision Cross-listed cs.CR Citations 3 Venue 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) Last Checked 4 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Computer Vision

πŸŒ… πŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV πŸ› ICCV πŸ“š 27.7K cites 11 years ago

Died the same way β€” πŸ‘» Ghosted