# FsaNet: Frequency Self-attention for Semantic Segmentation

Source: [FsaNet: Frequency Self-attention for Semantic Segmentation](<https://www.sota2.com/research/paper/68fa70271e209131cea496e4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:35:15.802Z

Authors: Fengyu Zhang, Ashkan Panahi, Guangjun Gao

Published: 2022-11-28T17:49:46.000Z

## Abstract

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 ($1\\times1$ convolution) stage and token mixing stage simultaneously. We show that frequency self-attention requires $87.29\\% \\sim 90.04\\%$ less memory, $96.13\\% \\sim 98.07\\%$ less FLOPs, and $97.56\\% \\sim 98.18\\%$ 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 \\url{https://github.com/zfy-csu/FsaNet

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.15595>)

[PDF](<https://arxiv.org/pdf/2211.15595.pdf>)