# FFT-based Dynamic Token Mixer for Vision

arXiv: https://arxiv.org/abs/2303.03932 · HTML: https://mlsanity.com/paper/2303.03932/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 75 references that are in the map.
- First posted on arXiv 7 Mar 2023.

## Builds on (most cited first, 30 of 59)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)

## Built on by (most cited first, 22 of 22)

- [EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2402.18302/) (2024)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [FSDENet: A Frequency and Spatial Domains based Detail Enhancement Network for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2510.00059/) (2025)
- [Complementary Advantages: Exploiting Cross-Field Frequency Correlation for NIR-Assisted Image Denoising](https://mlsanity.com/paper/2412.16645/) (2024)
- [FREAK: Frequency-modulated High-fidelity and Real-time Audio-driven Talking Portrait Synthesis](https://mlsanity.com/paper/2503.04067/) (2025)
- [FourierSR: A Fourier Token-based Plugin for Efficient Image Super-Resolution](https://mlsanity.com/paper/2503.10043/) (2025)
- [Dynamic Frequency Feature Fusion Network for Multi-Source Remote Sensing Data Classification](https://mlsanity.com/paper/2507.04510/) (2025)
- [Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics](https://mlsanity.com/paper/2408.01701/) (2024)
- [Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection](https://mlsanity.com/paper/2411.18409/) (2024)
- [Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detection](https://mlsanity.com/paper/2411.03728/) (2024)
- [Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation](https://mlsanity.com/paper/2411.19297/) (2024)
- [DAGNet: A Dual-View Attention-Guided Network for Efficient X-ray Security Inspection](https://mlsanity.com/paper/2502.01710/) (2025)
- [Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation](https://mlsanity.com/paper/2505.11909/) (2025)
- [FSGNet: A Frequency-Aware and Semantic Guidance Network for Infrared Small Target Detection](https://mlsanity.com/paper/2603.25389/) (2026)
- [CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling](https://mlsanity.com/paper/2607.05177/) (2026)
- [Spectral-Adaptive Modulation Networks for Visual Perception](https://mlsanity.com/paper/2503.23947/) (2025)
- [Forgery Guided Learning Strategy with Dual Perception Network for Deepfake Cross-domain Detection](https://mlsanity.com/paper/2508.10741/) (2025)
- [Shaken or Stirred? An Analysis of MetaFormer's Token Mixing for Medical Imaging](https://mlsanity.com/paper/2510.05971/) (2025)
- [Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation](https://mlsanity.com/paper/2603.24134/) (2026)
- [FreqTrack: Frequency Learning based Vision Transformer for RGB-Event Object Tracking](https://mlsanity.com/paper/2604.14526/) (2026)
- [Improving Radio Interferometry Imaging by Explicitly Modeling Cross-Domain Consistency in Reconstruction](https://mlsanity.com/paper/2604.16794/) (2026)
- [Denoising the Future: Context-Aware Spectral Diffusion for Temporal Knowledge Graph Extrapolation](https://mlsanity.com/paper/2608.20804/) (2026)

## Abstract (arXiv)

Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing, especially when dealing with high-resolution images. New types of token-mixer are proposed as an alternative to MHSA to circumvent this problem: an FFT-based token-mixer involves global operations similar to MHSA but with lower computational complexity. However, despite its attractive properties, the FFT-based token-mixer has not been carefully examined in terms of its compatibility with the rapidly evolving MetaFormer architecture. Here, we propose a novel token-mixer called Dynamic Filter and novel image recognition models, DFFormer and CDFFormer, to close the gaps above. The results of image classification and downstream tasks, analysis, and visualization show that our models are helpful. Notably, their throughput and memory efficiency when dealing with high-resolution image recognition is remarkable. Our results indicate that Dynamic Filter is one of the token-mixer options that should be seriously considered. The code is available at https://github.com/okojoalg/dfformer