# DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

arXiv: https://arxiv.org/abs/2308.06622 · HTML: https://mlsanity.com/paper/2308.06622/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 12 Aug 2023.

## Builds on (most cited first, 21 of 21)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Can contrastive learning avoid shortcut solutions?](https://mlsanity.com/paper/2106.11230/) (2021)
- [AugMax: Adversarial Composition of Random Augmentations for Robust Training](https://mlsanity.com/paper/2110.13771/) (2021)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain](https://mlsanity.com/paper/2108.08487/) (2021)
- [Automatic Shortcut Removal for Self-Supervised Representation Learning](https://mlsanity.com/paper/2002.08822/) (2020)
- [What do neural networks learn in image classification? A frequency shortcut perspective](https://mlsanity.com/paper/2307.09829/) (2023)
- [Mitigating Dataset Bias by Using Per-sample Gradient](https://mlsanity.com/paper/2205.15704/) (2022)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [How Does Frequency Bias Affect the Robustness of Neural Image Classifiers against Common Corruption and Adversarial Perturbations?](https://mlsanity.com/paper/2205.04533/) (2022)
- [Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform](https://mlsanity.com/paper/1811.05819/) (2018)
- [Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration](https://mlsanity.com/paper/2202.12412/) (2022)
- [Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain](https://mlsanity.com/paper/2207.10002/) (2022)

## Built on by (most cited first, 4 of 4)

- [Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification](https://mlsanity.com/paper/2403.01944/) (2024)
- [Do ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalization](https://mlsanity.com/paper/2503.03519/) (2025)
- [Exploring connections of spectral analysis and transfer learning in medical imaging](https://mlsanity.com/paper/2407.11379/) (2024)
- [Frequency Prior Guided Matching: A Data Augmentation Approach for Generalizable Semi-Supervised Polyp Segmentation](https://mlsanity.com/paper/2508.06517/) (2025)

## Abstract (arXiv)

Neural networks are prone to learn easy solutions from superficial statistics in the data, namely shortcut learning, which impairs generalization and robustness of models. We propose a data augmentation strategy, named DFM-X, that leverages knowledge about frequency shortcuts, encoded in Dominant Frequencies Maps computed for image classification models. We randomly select X% training images of certain classes for augmentation, and process them by retaining the frequencies included in the DFMs of other classes. This strategy compels the models to leverage a broader range of frequencies for classification, rather than relying on specific frequency sets. Thus, the models learn more deep and task-related semantics compared to their counterpart trained with standard setups. Unlike other commonly used augmentation techniques which focus on increasing the visual variations of training data, our method targets exploiting the original data efficiently, by distilling prior knowledge about destructive learning behavior of models from data. Our experimental results demonstrate that DFM-X improves robustness against common corruptions and adversarial attacks. It can be seamlessly integrated with other augmentation techniques to further enhance the robustness of models.