English

HarmoniAD: Harmonizing Local Structures and Global Semantics for Anomaly Detection

Computer Vision and Pattern Recognition 2026-01-05 v1 Artificial Intelligence

Abstract

Anomaly detection is crucial in industrial product quality inspection. Failing to detect tiny defects often leads to serious consequences. Existing methods face a structure-semantics trade-off: structure-oriented models (such as frequency-based filters) are noise-sensitive, while semantics-oriented models (such as CLIP-based encoders) often miss fine details. To address this, we propose HarmoniAD, a frequency-guided dual-branch framework. Features are first extracted by the CLIP image encoder, then transformed into the frequency domain, and finally decoupled into high- and low-frequency paths for complementary modeling of structure and semantics. The high-frequency branch is equipped with a fine-grained structural attention module (FSAM) to enhance textures and edges for detecting small anomalies, while the low-frequency branch uses a global structural context module (GSCM) to capture long-range dependencies and preserve semantic consistency. Together, these branches balance fine detail and global semantics. HarmoniAD further adopts a multi-class joint training strategy, and experiments on MVTec-AD, VisA, and BTAD show state-of-the-art performance with both sensitivity and robustness.

Keywords

Cite

@article{arxiv.2601.00327,
  title  = {HarmoniAD: Harmonizing Local Structures and Global Semantics for Anomaly Detection},
  author = {Naiqi Zhang and Chuancheng Shi and Jingtong Dou and Wenhua Wu and Fei Shen and Jianhua Cao},
  journal= {arXiv preprint arXiv:2601.00327},
  year   = {2026}
}
R2 v1 2026-07-01T08:47:49.028Z