SOURCE-LINKED INTELLIGENCE

Mitigating Shortcut Learning: Texture-Penalized Prototype Networks

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Standard Convolutional Neural Networks (CNNs) exhibit severe performance degradation due to a strong inductive texture bias that prioritizes local, high-frequency patterns over global structural shapes. This dependency causes confident misclassifications during textural changes or environmental effects. To address this flaw, this study introduces the Texture-Penalized Prototype Network (TPPN), a novel architectural framework that shifts this inherent bias without depending on resource-intensive augmented datasets. Specifically, a Texture-Penalization Branch (TPB) imposes a penalty to suppress

Read original source ↗ Open in workspace

recordType

paper

region

Global