# Deep Frequency Filtering for Domain Generalization

arXiv: https://arxiv.org/abs/2203.12198 · HTML: https://mlsanity.com/paper/2203.12198/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 90 of its 117 references that are in the map.
- First posted on arXiv 23 Mar 2022.

## Builds on (most cited first, 30 of 90)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)

## Built on by (most cited first, 30 of 43)

- [Frequency-Spatial Entanglement Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2409.01686/) (2024)
- [Adaptive Frequency Filters As Efficient Global Token Mixers](https://mlsanity.com/paper/2307.14008/) (2023)
- [Domain-invariant Feature Exploration for Domain Generalization](https://mlsanity.com/paper/2207.12020/) (2022)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples](https://mlsanity.com/paper/2410.10365/) (2024)
- [Frequency Dynamic Convolution for Dense Image Prediction](https://mlsanity.com/paper/2503.18783/) (2025)
- [MLP Can Be A Good Transformer Learner](https://mlsanity.com/paper/2404.05657/) (2024)
- [Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2410.22135/) (2024)
- [Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification](https://mlsanity.com/paper/2410.06977/) (2024)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2409.12522/) (2024)
- [CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification](https://mlsanity.com/paper/2501.16065/) (2025)
- [START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation](https://mlsanity.com/paper/2410.16020/) (2024)
- [Neural Fourier Modelling: A Highly Compact Approach to Time-Series Analysis](https://mlsanity.com/paper/2410.04703/) (2024)
- [AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2501.03074/) (2025)
- [FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis](https://mlsanity.com/paper/2503.04067/) (2025)
- [Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2305.17939/) (2023)
- [ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models](https://mlsanity.com/paper/2406.01432/) (2024)
- [PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification](https://mlsanity.com/paper/2504.19136/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts](https://mlsanity.com/paper/2401.11406/) (2024)
- [Revisiting Spurious Correlation in Domain Generalization](https://mlsanity.com/paper/2406.11517/) (2024)
- [Soft Segmented Randomization: Enhancing Domain Generalization in SAR-ATR for Synthetic-to-Measured](https://mlsanity.com/paper/2409.14060/) (2024)
- [IRASNet: Improved Feature-Level Clutter Reduction for Domain Generalized SAR-ATR](https://mlsanity.com/paper/2409.16845/) (2024)
- [FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2505.08349/) (2025)
- [MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition](https://mlsanity.com/paper/2507.00430/) (2025)
- [Deep Edge Filter: Return of the Human-Crafted Layer in Deep Learning](https://mlsanity.com/paper/2510.13865/) (2025)
- [ReText: Text Boosts Generalization in Image-Based Person Re-identification](https://mlsanity.com/paper/2602.05785/) (2026)
- [Patch-aware Batch Normalization for Improving Cross-domain Robustness](https://mlsanity.com/paper/2304.02848/) (2023)
- [Frequency Decomposition to Tap the Potential of Single Domain for Generalization](https://mlsanity.com/paper/2304.07261/) (2023)

## Abstract (arXiv)

Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency components in the learning process and indicated that this may affect the robustness of learned features. In this paper, we propose Deep Frequency Filtering (DFF) for learning domain-generalizable features, which is the first endeavour to explicitly modulate the frequency components of different transfer difficulties across domains in the latent space during training. To achieve this, we perform Fast Fourier Transform (FFT) for the feature maps at different layers, then adopt a light-weight module to learn attention masks from the frequency representations after FFT to enhance transferable components while suppressing the components not conducive to generalization. Further, we empirically compare the effectiveness of adopting different types of attention designs for implementing DFF. Extensive experiments demonstrate the effectiveness of our proposed DFF and show that applying our DFF on a plain baseline outperforms the state-of-the-art methods on different domain generalization tasks, including close-set classification and open-set retrieval.