EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HiFRA-AD: High-Frequency Residual-Aware Sparse Refinement for Unsupervised Industrial Anomaly Detection

Yangu Chen

Symmetry · 17.11.2026 · 18 (11) · 1922

DOI: 10.3390/sym18111922 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 17.11.2026. Verfasst von Yangu Chen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Symmetry and repetitive patterns are common in industrial products, where small defects often disrupt local structural regularity. Fixed-resolution reconstruction can weaken this evidence, while high-resolution cropping changes visual context and anomaly-score distributions. We propose HiFRA-AD, a high-frequency residual-aware sparse refinement framework that couples local feature sensitivity with calibrated evidence aggregation. A fixed-coefficient token-grid residual operator enhances local spatial variation before reconstruction using a frozen DINOv2 encoder. At inference, the global anomaly map selects four peak-suppressed regions for re-evaluation by the shared model. Robust median/quantile alignment and a soft evidence gate convert the local responses into nonnegative residual updates. HiFRA-AD-S achieves P-AP/AUPRO scores of 71.6/95.5, 55.1/96.1, and 46.8/59.8 on MVTec AD, VisA, and MVTec AD 2, respectively. The MVTec AD 2 evaluation uses the official 2045-image TESTpriv partition and AU-PRO@0.30. In backbone-matched MVTec AD comparisons, P-AP improves from 67.5 to 71.6 with ViT-S and from 69.3 to 72.8 with ViT-B. Five paired ViT-S training runs yield a 4.10-point P-AP gain (95% CI [3.95, 4.25]) and a 1.10-point AUPRO gain (95% CI [0.98, 1.22]). With four local regions, ViT-S inference takes 20.8 ms per image on an RTX 4090, compared with 10.0 ms for the global baseline. A defect-subtype analysis records larger paired per-image AP gains for structural disruptions (+4.99 points) than for other anomalies (+2.68 points). These results support selective local refinement for fine-grained industrial anomaly localization.

Zitieren

APA

Chen, Y. (2026). HiFRA-AD: High-Frequency Residual-Aware Sparse Refinement for Unsupervised Industrial Anomaly Detection. Symmetry, 18(11), 1922. https://doi.org/10.3390/sym18111922

Vancouver

Chen Y. HiFRA-AD: High-Frequency Residual-Aware Sparse Refinement for Unsupervised Industrial Anomaly Detection. Symmetry. 2026;18(11):1922. doi:10.3390/sym18111922

BibTeX
@article{Chen2026,
  author = {Chen, Yangu},
  title = {HiFRA-AD: High-Frequency Residual-Aware Sparse Refinement for Unsupervised Industrial Anomaly Detection},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {11},
  pages = {1922},
  doi = {10.3390/sym18111922}
}
Kostenlos starten →