WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Guoan, Xiao, Yang, Jia, Wenjing, Gao, Guangwei, Qi, Guo-Jun, Lin, Chia-Wen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909867162206208
author Xu, Guoan
Xiao, Yang
Jia, Wenjing
Gao, Guangwei
Qi, Guo-Jun
Lin, Chia-Wen
author_facet Xu, Guoan
Xiao, Yang
Jia, Wenjing
Gao, Guangwei
Qi, Guo-Jun
Lin, Chia-Wen
contents While recent semantic segmentation networks heavily rely on powerful pretrained encoders, most employ simplistic decoders, leading to suboptimal trade-offs between semantic context and fine-grained detail preservation. To address this, we propose a novel decoder architecture, WaveSeg, which jointly optimizes feature refinement in spatial and wavelet domains. Specifically, high-frequency components are first learned from input images as explicit priors to reinforce boundary details at early stages. A multi-scale fusion mechanism, Dual Domain Operation (DDO), is then applied, and the novel Spectrum Decomposition Attention (SDA) block is proposed, which is developed to leverage Mamba's linear-complexity long-range modeling to enhance high-frequency structural details. Meanwhile, reparameterized convolutions are applied to preserve low-frequency semantic integrity in the wavelet domain. Finally, a residual-guided fusion integrates multi-scale features with boundary-aware representations at native resolution, producing semantically and structurally rich feature maps. Extensive experiments on standard benchmarks demonstrate that WaveSeg, leveraging wavelet-domain frequency prior with Mamba-based attention, consistently outperforms state-of-the-art approaches both quantitatively and qualitatively, achieving efficient and precise segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21079
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition
Xu, Guoan
Xiao, Yang
Jia, Wenjing
Gao, Guangwei
Qi, Guo-Jun
Lin, Chia-Wen
Computer Vision and Pattern Recognition
While recent semantic segmentation networks heavily rely on powerful pretrained encoders, most employ simplistic decoders, leading to suboptimal trade-offs between semantic context and fine-grained detail preservation. To address this, we propose a novel decoder architecture, WaveSeg, which jointly optimizes feature refinement in spatial and wavelet domains. Specifically, high-frequency components are first learned from input images as explicit priors to reinforce boundary details at early stages. A multi-scale fusion mechanism, Dual Domain Operation (DDO), is then applied, and the novel Spectrum Decomposition Attention (SDA) block is proposed, which is developed to leverage Mamba's linear-complexity long-range modeling to enhance high-frequency structural details. Meanwhile, reparameterized convolutions are applied to preserve low-frequency semantic integrity in the wavelet domain. Finally, a residual-guided fusion integrates multi-scale features with boundary-aware representations at native resolution, producing semantically and structurally rich feature maps. Extensive experiments on standard benchmarks demonstrate that WaveSeg, leveraging wavelet-domain frequency prior with Mamba-based attention, consistently outperforms state-of-the-art approaches both quantitatively and qualitatively, achieving efficient and precise segmentation.
title WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.21079