StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection

• URL: http://arxiv.org/abs/2602.17048v2
• Date: Sat, 21 Feb 2026 14:52:53 GMT
• Title: StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection
• Abstract summary: Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD)<n>We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling.
• Score: 5.925242470217676
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it relies on a single extreme response, it discards most information about how anomaly evidence is distributed and structured across the image, often causing normal and anomalous scores to overlap. We propose StructCore, a training-free, structure-aware image-level scoring method that goes beyond max pooling. Given an anomaly score map, StructCore computes a low-dimensional structural descriptor phi(S) that captures distributional and spatial characteristics, and refines image-level scoring via a diagonal Mahalanobis calibration estimated from train-good samples, without modifying pixel-level localization. StructCore achieves image-level AUROC scores of 99.6% on MVTec AD and 98.4% on VisA, demonstrating robust image-level anomaly detection by exploiting structural signatures missed by max pooling.

Related papers

• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection [52.986874008247554]
  We propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes.<n>ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation.<n>It achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets.
  arXiv  Detail & Related papers  (2026-08-01T04:46:55Z)
• StructDiff: A Structure-Preserving and Spatially Controllable Diffusion Model for Single-Image Generation [72.84181869780627]
  StructDiff is a generative framework based on a single-scale diffusion model for single-image generation.<n>It incorporates 3D positional encoding (PE) as a spatial prior, allowing flexible control over positions, scale, and local details of generated objects.<n>It also demonstrates broad applicability across downstream tasks, such as text-guided image generation, image editing, outpainting, and paint-to-image synthesis.
  arXiv  Detail & Related papers  (2026-04-14T10:55:43Z)
• SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling [6.476948781728136]
  SubspaceAD is a training-free method for detecting visual anomalies in industrial images.<n>It works across one-shot and few-shot settings without training, prompt tuning, or memory banks.<n>It achieves image-level and pixel-level AUROC of 98.0% and 97.6% on the MVTec-AD dataset, and 93.3% and 98.3% on the VisA dataset.
  arXiv  Detail & Related papers  (2026-02-26T13:52:57Z)
• Structural damage detection via hierarchical damage information with volumetric assessment [1.4470320778878742]
  Structural health monitoring (SHM) is essential for ensuring the safety and longevity of infrastructure.<n>This study introduces the Guided Detection Network (Guided-DetNet), a framework designed to address these challenges.<n>Guided-DetNet is characterized by a Generative Attention Module (GAM), Hierarchical Elimination Algorithm (HEA), and Volumetric Contour Visual Assessment (VCVA)
  arXiv  Detail & Related papers  (2024-07-29T04:33:04Z)
• A Hierarchically Feature Reconstructed Autoencoder for Unsupervised Anomaly Detection [8.512184778338806]
  It consists of a well pre-trained encoder to extract hierarchical feature representations and a decoder to reconstruct these intermediate features from the encoder. The anomalies can be detected when the decoder fails to reconstruct features well, and then errors of hierarchical feature reconstruction are aggregated into an anomaly map to achieve anomaly localization. Experiment results show that the proposed method outperforms the state-of-the-art methods on MNIST, Fashion-MNIST, CIFAR-10, and MVTec Anomaly Detection datasets.
  arXiv  Detail & Related papers  (2024-05-15T07:20:27Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• Adapting the Hypersphere Loss Function from Anomaly Detection to Anomaly Segmentation [1.9458156037869137]
  We propose an incremental improvement to Fully Convolutional Data Description (FCDD) FCDD is an adaptation of the one-class classification approach from anomaly detection to image anomaly segmentation (a.k.a. anomaly localization) We analyze its original loss function and propose a substitute that better resembles its predecessor, the Hypersphere (HSC)
  arXiv  Detail & Related papers  (2023-01-23T18:06:35Z)
• U-Flow: A U-shaped Normalizing Flow for Anomaly Detection with Unsupervised Threshold [0.40964539027092906]
  We propose a one-class self-supervised method for anomaly segmentation in images. It benefits from a modern machine learning approach and a more classic statistical detection theory. The proposed approach produces state-of-the-art results for all metrics and all datasets.
  arXiv  Detail & Related papers  (2022-11-22T15:43:19Z)
• Occlusion-Aware Instance Segmentation via BiLayer Network Architectures [73.45922226843435]
  We propose Bilayer Convolutional Network (BCNet), where the top layer detects occluding objects (occluders) and the bottom layer infers partially occluded instances (occludees) We investigate the efficacy of bilayer structure using two popular convolutional network designs, namely, Fully Convolutional Network (FCN) and Graph Convolutional Network (GCN)
  arXiv  Detail & Related papers  (2022-08-08T21:39:26Z)
• Self-Supervised Training with Autoencoders for Visual Anomaly Detection [61.62861063776813]
  We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. We adapt a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. We achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.
  arXiv  Detail & Related papers  (2022-06-23T14:16:30Z)
• AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-based Encoder-Decoder [3.31490164885582]
  We propose a vision transformer-based encoder-decoder model, named AnoViT, to reflect normal information by additionally learning the global relationship between image patches. The proposed model performed better than the convolution-based model on three benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-21T09:01:37Z)
• Unsupervised Learning of Multi-level Structures for Anomaly Detection [16.037822355038443]
  This paper introduces a novel method to generate anomalous data by breaking up global structures. It can efficiently expose local abnormal structures of various levels. By aggregating the outputs of all level-specific detectors, we obtain a model that can detect all potential anomalies.
  arXiv  Detail & Related papers  (2021-04-25T08:38:41Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)
• Self-Learning with Rectification Strategy for Human Parsing [73.06197841003048]
  We propose a trainable graph reasoning method to correct two typical errors in the pseudo-labels. The reconstructed features have a stronger ability to represent the topology structure of the human body. Our method outperforms other state-of-the-art methods in supervised human parsing tasks.
  arXiv  Detail & Related papers  (2020-04-17T03:51:30Z)
• High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification [84.43394420267794]
  We propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. Our framework significantly outperforms state-of-the-art by6.5%mAP scores on Occluded-Duke dataset.
  arXiv  Detail & Related papers  (2020-03-18T12:18:35Z)
• Weakly-Supervised Salient Object Detection via Scribble Annotations [54.40518383782725]
  We propose a weakly-supervised salient object detection model to learn saliency from scribble labels. We present a new metric, termed saliency structure measure, to measure the structure alignment of the predicted saliency maps. Our method not only outperforms existing weakly-supervised/unsupervised methods, but also is on par with several fully-supervised state-of-the-art models.
  arXiv  Detail & Related papers  (2020-03-17T12:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.