aiqbench analysis
This research identifies a critical vulnerability in texture-driven visual learning tasks where neural networks rely disproportionately on low-frequency components, leading to poor generalization. By pruning these specific low-frequency shortcuts, the study demonstrates significant improvements in both in-distribution and out-of-distribution accuracy without requiring larger foundation models. The findings offer practical guidance for practitioners developing computer vision systems in domains where standard shape-driven benchmarks may not apply.
Low-Frequency Shortcuts in Texture-Driven Visual Learning
arXiv:2606.03493v2 Announce Type: replace-cross Abstract: Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets. Existing studies are all based on a few standard benchmarks, which are shape-driven. Numerous application domains, however, are texture-driven. In this work, we present shortcut learning analysis for texture-driven domains and compare it with that of a standard benchmark. We show that texture-driven domains suffer from low-frequency shortcuts. They make the majority of their decisions based on a few low-frequency components (LFCs) with a skewed spectral behavior, despite that higher-frequency components (HFCs) have higher predictive power. Pruning LFCs from training and test sets mitigates the shortcut and provides a more balanced spectral behavior, improving the ID accuracy by up to 10% and OOD accuracy by up to 40% under algorithmic and real-world domain shifts. We show that general-purpose and domain-specific foundation models can also suffer from low-frequency shortcuts. While large models can mitigate the shortcuts, they incur a high computational cost and may result in a significantly lower accuracy than shortcut-pruned from-scratch trained small models. We show that reduced image resolutions amplify the degree of shortcuts; large frequency-transformation block sizes capture low-frequency shortcuts better than small block sizes; and, low-frequency shortcuts persist across different color spaces. Our findings provide valuable insights, which we hope will be useful for practitioners working on new, understudied domains.
Abstract:Neural networks suffer from shortcut learning, where learned features generalize well to the training set but not to in-distribution (ID) or out-of-distribution (OOD) test sets. Existing studies are all based on a few standard benchmarks, which are shape-driven. Numerous application domains, however, are texture-driven. In this work, we present shortcut learning analysis for texture-driven domains and compare it with that of a standard benchmark. We show that texture-driven domains suffer from low-frequency shortcuts. They make the majority of their decisions based on a few low-frequency components (LFCs) with a skewed spectral behavior, despite that higher-frequency components (HFCs) have higher predictive power. Pruning LFCs from training and test sets mitigates the shortcut and provides a more balanced spectral behavior, improving the ID accuracy by up to 10% and OOD accuracy by up to 40% under algorithmic and real-world domain shifts. We show that general-purpose and domain-specific foundation models can also suffer from low-frequency shortcuts. While large models can mitigate the shortcuts, they incur a high computational cost and may result in a significantly lower accuracy than shortcut-pruned from-scratch trained small models. We show that reduced image resolutions amplify the degree of shortcuts; large frequency-transformation block sizes capture low-frequency shortcuts better than small block sizes; and, low-frequency shortcuts persist across different color spaces. Our findings provide valuable insights, which we hope will be useful for practitioners working on new, understudied domains.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2606.03493 [cs.CV]
(or arXiv:2606.03493v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.03493 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 327 words
Related coverage
Low-Frequency Shortcuts in Texture-Driven Visual Learning
arXiv · Jun 3, 2026
ColoACT: Multi-Cue Action Chunking for Smooth Autonomous Colon Navigation on a Self-Propelled Endoscopic Robot
arXiv · Oct 2, 2026
ORBIT-2 based Weather and Climate Downscaling and Downscaled Global Forecasts on AMD Instinct
AMD · Jun 8, 2026
2026.5: We're on the same frequency now 📡
Home Assistant · May 6, 2026