# FsaNet: Frequency Self-attention for Semantic Segmentation

arXiv: https://arxiv.org/abs/2211.15595 · HTML: https://mlsanity.com/paper/2211.15595/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 70 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 30 of 60)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond](https://mlsanity.com/paper/1904.11492/) (2019)

## Built on by (most cited first, 10 of 10)

- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Adaptive Frequency Enhancement Network for Remote Sensing Image Semantic Segmentation](https://mlsanity.com/paper/2504.02647/) (2025)
- [ShareCMP: Polarization-Aware RGB-P Semantic Segmentation](https://mlsanity.com/paper/2312.03430/) (2023)
- [Spatial-Frequency Dual Progressive Attention Network For Medical Image Segmentation](https://mlsanity.com/paper/2406.07952/) (2024)
- [Expose Camouflage in the Water: Underwater Camouflaged Instance Segmentation and Dataset](https://mlsanity.com/paper/2510.17585/) (2025)
- [Large coordinate kernel attention network for lightweight image super-resolution](https://mlsanity.com/paper/2405.09353/) (2024)
- [A Gift from the Integration of Discriminative and Diffusion-based Generative Learning: Boundary Refinement Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2507.01573/) (2025)
- [SAIP-Net: Enhancing Remote Sensing Image Segmentation via Spectral Adaptive Information Propagation](https://mlsanity.com/paper/2504.16564/) (2025)
- [Efficient Star Distillation Attention Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2506.12475/) (2025)
- [Hierarchical MLANet: Multi-level Attention for 3D Face Reconstruction From Single Images](https://mlsanity.com/paper/2509.10024/) (2025)

## Abstract (arXiv)

Considering the spectral properties of images, we propose a new self-attention mechanism with highly reduced computational complexity, up to a linear rate. To better preserve edges while promoting similarity within objects, we propose individualized processes over different frequency bands. In particular, we study a case where the process is merely over low-frequency components. By ablation study, we show that low frequency self-attention can achieve very close or better performance relative to full frequency even without retraining the network. Accordingly, we design and embed novel plug-and-play modules to the head of a CNN network that we refer to as FsaNet. The frequency self-attention 1) requires only a few low frequency coefficients as input, 2) can be mathematically equivalent to spatial domain self-attention with linear structures, 3) simplifies token mapping (1×1 convolution) stage and token mixing stage simultaneously. We show that frequency self-attention requires 87.29% ~ 90.04% less memory, 96.13% ~ 98.07% less FLOPs, and 97.56% ~ 98.18% in run time than the regular self-attention. Compared to other ResNet101-based self-attention networks, ourM achieves a new sArt result (83.0% mIoU) on Cityscape test dataset and competitive results on ADE20k and VOCaug. ourM can also enhance MASK R-CNN for instance segmentation on COCO. In addition, utilizing the proposed module, Segformer can be boosted on a series of models with different scales, and Segformer-B5 can be improved even without retraining. Code is accessible at urlhttps://github.com/zfy-csu/FsaNet