The results demonstrate that combining multiple compact normal-data subspaces improves discrimination and reduces reliance on the evaluated single random representation while retaining a lightweight, anomaly-label-free training procedure.
Abstract
Industrial anomaly detection is commonly performed under one-class conditions because defective samples are scarce or unavailable during training. This study presents a lightweight one-class anomaly detection framework that reduces the dependence of compact deep representations on a single arbitrarily selected feature subset. Intermediate features extracted from a frozen MobileNetV2 backbone are divided into five independently sampled 100-channel subspaces. A position-specific diagonal Gaussian model is fitted separately to each subspace using only normal training images. The resulting anomaly scores are robustly normalized and combined through a normal-calibrated reliability-weighting strategy, while image-level decisions are obtained from the highest-scoring local patches. To prevent information leakage, operating thresholds are determined through five-fold cross-fitted calibration using only normal training scores. The proposed compact random-subspace ensemble was evaluated on all 15 categories of MVTec AD and externally validated on the 12-category VisA benchmark. On MVTec AD, the ensemble increased the macro ROC-AUC from 0.9350 to 0.9437 and the macro F1 score from 0.8366 to 0.8504 compared with a single random 100-channel subspace. External validation on VisA showed the same improvement trend, with higher macro ROC-AUC, AP, and F1 values than the single-subspace configuration. The results demonstrate that combining multiple compact normal-data subspaces improves discrimination and reduces reliance on the evaluated single random representation while retaining a lightweight, anomaly-label-free training procedure.
SPARC is presented, a few-shot calibration method that intercepts patch features between encoder and detector and removes a closed-form, spatially indexed estimate of deployment-time nuisance through per-cell subspace projection and uses the algebraic saturation rank on the encoder's native patch grid.
Seokhee Han, Seung-Jun Chu, Mateusz Nowak et al.· 1 citation
A representation-enhanced AD model with prototype learning and neighborhood rough set (ADPLN) is proposed, which outperforms the state-of-the-art methods and designs a sample-prototype correlation objective function to promote the learning of discriminative representations of normals and mitigate the negative impacts o...
Jiao-Long Chen, Ye Liu, Yu-Hua Qian et al.· IEEE Transactions on Cyberne...· 0 citations
LLM-Detector is proposed, a framework that utilizes the in-context learning capacity of LLMs for structured, prompt-conditioned scoring synthesis, enabling LLMs to derive anomaly detection logic from structured normal-state knowledge.
Tu Nguyen, Dang Nguyen, T. D. Le et al.· 0 citations
A Memory-Augmented Autoencoder that combines a U-Net reconstruction component with a patch-level memory bank for nearest-neighbor-based anomaly scoring and outperforming the reconstruction component in AUC-ROC, which is attributable to the robustness of patch-level memory matching for localized structural defects.
Hai Son, D. Ngo· International Journal of Adv...· 0 citations
This work shows that counting ability can be introduced into training-free anomaly detection without additional training or part-level supervision, and proposes a normal-set calibration that aligns heterogeneous anomaly cues using statistics from normal images, enabling their direct fusion within a unified training-fre...
Chang-Yi Li, Miao Yu, Kai-Ling Dong et al.· 0 citations
Unsupervised industrial anomaly detection learns from normal images and identifies defects unseen during training. In reconstruction-based detectors, the features used to represent normality and the residuals used to localize defects vary across images, yet these signals are commonly selected with fixed category-level...
Chen-Yang Zhang, Fang-Qi Zhou, Yu Wang et al.· Symmetry· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.