EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FSQR-Former: A Frequency–Spatial Query Refinement Transformer with Feature Feedback for Surface Defect Segmentation

Yang Yang, Xiaohui Zhu, Hongxi Guo, Wei Liu, Guangqiu Chen, Yongjian Yang

Electronics · 29.10.2026 · 15 (21) · 5023

DOI: 10.3390/electronics15215023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 29.10.2026. Verfasst von Yang Yang und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Province Science and Technology Department.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate surface defect segmentation remains challenging when thin and low-contrast defects are embedded in repetitive textures, where local frequency variations may originate from both defects and background structures. This work presents FSQR-Former, a query-based mask-classification transformer that couples frequency–spatial query refinement with cross-stage feature feedback. Content-Decoupled Directional Wavelet Frequency Attention (CDWFA) applies Haar decomposition to visual features without explicitly added positional encodings and combines directional calibration with frequency gating informed by low-frequency context. Multi-Scale Query-Guided Sparse Attention (MS-QSA) enriches spatial features with neighborhood context and selectively aggregates tokens according to query compatibility. Query-to-Feature Feedback Modulation (Q2FM) converts refined query states into channel and spatial modulation signals for finer-scale features, coupling query refinement with feature recalibration during coarse-to-fine decoding. The three-run mean results of FSQR-Former indicate competitive benchmark performance on ESDIs-SOD and CrackSeg9k, with the best scores across all five evaluation metrics on ZJU-Leaper. Controlled ablations support the contributions of joint frequency–spatial refinement and query-conditioned feature feedback to pixel-wise accuracy and structural agreement. Complexity analysis further indicates a favorable balance between segmentation accuracy, computational cost, and parameter count.

Förderung

  • Jilin Province Science and Technology Department

Zitieren

APA

Yang, Y., Zhu, X., Guo, H., Liu, W., Chen, G., & Yang, Y. (2026). FSQR-Former: A Frequency–Spatial Query Refinement Transformer with Feature Feedback for Surface Defect Segmentation. Electronics, 15(21), 5023. https://doi.org/10.3390/electronics15215023

Vancouver

Yang Y, Zhu X, Guo H, Liu W, Chen G, Yang Y. FSQR-Former: A Frequency–Spatial Query Refinement Transformer with Feature Feedback for Surface Defect Segmentation. Electronics. 2026;15(21):5023. doi:10.3390/electronics15215023

BibTeX
@article{Yang2026,
  author = {Yang, Yang and Zhu, Xiaohui and Guo, Hongxi and Liu, Wei and Chen, Guangqiu and Yang, Yongjian},
  title = {FSQR-Former: A Frequency–Spatial Query Refinement Transformer with Feature Feedback for Surface Defect Segmentation},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5023},
  doi = {10.3390/electronics15215023}
}
Kostenlos starten →