# SPANet: Frequency-balancing Token Mixer using Spectral Pooling Aggregation Modulation

arXiv: https://arxiv.org/abs/2308.11568 · HTML: https://mlsanity.com/paper/2308.11568/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 67 of its 82 references that are in the map.
- First posted on arXiv 22 Aug 2023.

## Builds on (most cited first, 30 of 67)

- [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)
- [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)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [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)
- [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)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)

## Built on by (most cited first, 14 of 14)

- [ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions](https://mlsanity.com/paper/2403.07392/) (2024)
- [Rewrite the Stars](https://mlsanity.com/paper/2403.19967/) (2024)
- [Frequency-Spatial Entanglement Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2409.01686/) (2024)
- [Frequency-Adaptive Dilated Convolution for Semantic Segmentation](https://mlsanity.com/paper/2403.05369/) (2024)
- [Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture](https://mlsanity.com/paper/2403.07347/) (2024)
- [Frequency-Dynamic Attention Modulation for Dense Prediction](https://mlsanity.com/paper/2507.12006/) (2025)
- [Task-Generalized Adaptive Cross-Domain Learning for Multimodal Image Fusion](https://mlsanity.com/paper/2508.15505/) (2025)
- [ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads](https://mlsanity.com/paper/2506.03433/) (2025)
- [Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots](https://mlsanity.com/paper/2502.03829/) (2025)
- [Spectral-Adaptive Modulation Networks for Visual Perception](https://mlsanity.com/paper/2503.23947/) (2025)
- [FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception](https://mlsanity.com/paper/2506.13501/) (2025)
- [Shaken or Stirred? An Analysis of MetaFormer's Token Mixing for Medical Imaging](https://mlsanity.com/paper/2510.05971/) (2025)
- [Latent-Info and Low-Dimensional Learning for Human Mesh Recovery and Parallel Optimization](https://mlsanity.com/paper/2510.18267/) (2025)
- [FU-Mamba: A Frequency-Enhanced Dynamic Scanning Framework for Oralscan Image Segmentation](https://mlsanity.com/paper/2608.26607/) (2026)

## Abstract (arXiv)

Recent studies show that self-attentions behave like low-pass filters (as opposed to convolutions) and enhancing their high-pass filtering capability improves model performance. Contrary to this idea, we investigate existing convolution-based models with spectral analysis and observe that improving the low-pass filtering in convolution operations also leads to performance improvement. To account for this observation, we hypothesize that utilizing optimal token mixers that capture balanced representations of both high- and low-frequency components can enhance the performance of models. We verify this by decomposing visual features into the frequency domain and combining them in a balanced manner. To handle this, we replace the balancing problem with a mask filtering problem in the frequency domain. Then, we introduce a novel token-mixer named SPAM and leverage it to derive a MetaFormer model termed as SPANet. Experimental results show that the proposed method provides a way to achieve this balance, and the balanced representations of both high- and low-frequency components can improve the performance of models on multiple computer vision tasks. Our code is available at hrefhttps://doranlyong.github.io/projects/spanet/https://doranlyong.github.io/projects/spanet/.