HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection

• URL: http://arxiv.org/abs/2602.09524v1
• Date: Tue, 10 Feb 2026 08:27:20 GMT
• Title: HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly Detection
• Authors: Han Zhou, Yuxuan Gao, Yinchao Du, Xuezhe Zheng,
• Abstract summary: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection.<n>We propose a high-low resolution guided feature alignment framework that learns normality by modeling cross-resolution feature consistency.<n>Experiments on standard benchmarks demonstrate the effectiveness of HLGFA, achieving 97.9% pixel-level AUROC and 97.5% image-level AUROC.
• Score: 10.362921219308207
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detection is required. In this paper, we propose HLGFA, a high-low resolution guided feature alignment framework that learns normality by modeling cross-resolution feature consistency between high-resolution and low-resolution representations of normal samples, instead of relying on pixel-level reconstruction. Dual-resolution inputs are processed by a shared frozen backbone to extract multi-level features, and high-resolution representations are decomposed into structure and detail priors to guide the refinement of low-resolution features through conditional modulation and gated residual correction. During inference, anomalies are naturally identified as regions where cross-resolution alignment breaks down. In addition, a noise-aware data augmentation strategy is introduced to suppress nuisance-induced responses commonly observed in industrial environments. Extensive experiments on standard benchmarks demonstrate the effectiveness of HLGFA, achieving 97.9% pixel-level AUROC and 97.5% image-level AUROC on the MVTec AD dataset, outperforming representative reconstruction-based and feature-based methods.

Related papers

• DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction [67.42242016220122]
  Digital subtraction angiography is a key imaging technique for the auxiliary diagnosis and treatment of cerebrovascular diseases.<n>Recent advancements in gaussian splatting and dynamic neural representations have enabled robust 3D vessel reconstruction from sparse dynamic inputs.<n>This paper proposes DSA-SRGS, the first super-resolution gaussian splatting framework for dynamic sparse-view DSA reconstruction.
  arXiv  Detail & Related papers  (2026-03-05T03:41:08Z)
• SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioning [59.013863248600046]
  We propose a spatially re-focused super-resolution framework that refines text conditioning at inference time.<n>Second, we introduce a Spatially Targeted-Free Guidance mechanism that selectively bypasses text influences on ungrounded pixels to prevent hallucinations.
  arXiv  Detail & Related papers  (2025-10-26T05:03:55Z)
• Towards High-Resolution Industrial Image Anomaly Detection [7.626097310990373]
  HiAD is a general framework for high-resolution anomaly detection.<n>It employs a dual-branch architecture that integrates anomaly cues across different scales.<n>It incorporates a multi-resolution feature fusion strategy to tackle the challenges posed by fine-grained texture variations in high-resolution images.
  arXiv  Detail & Related papers  (2025-08-18T13:54:29Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• Region-Aware CAM: High-Resolution Weakly-Supervised Defect Segmentation via Salient Region Perception [2.9962030276180758]
  This paper proposes a novel weakly supervised semantic segmentation framework.<n>It consists of a region-aware class activation map (CAM) and pseudo-label training.<n>The proposed framework effectively bridges the gap between weakly supervised learning and high-precision defect segmentation.
  arXiv  Detail & Related papers  (2025-06-28T12:24:45Z)
• Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift [51.24522135151649]
  Anomaly detection plays a crucial role in quality control for industrial applications.<n>Existing methods attempt to address domain shifts by training generalizable models.<n>Our proposed method demonstrates superior results compared with state-of-the-art anomaly detection and domain adaptation methods.
  arXiv  Detail & Related papers  (2025-03-19T05:25:52Z)
• PA-CLIP: Enhancing Zero-Shot Anomaly Detection through Pseudo-Anomaly Awareness [10.364634539199422]
  We introduce PA-CLIP, a zero-shot anomaly detection method that reduces background noise and enhances defect detection through a pseudo-anomaly-based framework.<n>The proposed method integrates a multiscale feature aggregation strategy for capturing detailed global and local information.<n>It outperforms existing zero-shot methods, providing a robust solution for industrial defect detection.
  arXiv  Detail & Related papers  (2025-03-03T08:29:27Z)
• Feature Attenuation of Defective Representation Can Resolve Incomplete Masking on Anomaly Detection [1.0358639819750703]
  In unsupervised anomaly detection (UAD) research, it is necessary to develop a computationally efficient and scalable solution. We revisit the reconstruction-by-inpainting approach and rethink to improve it by analyzing strengths and weaknesses. We propose Feature Attenuation of Defective Representation (FADeR) that only employs two layers which attenuates feature information of anomaly reconstruction.
  arXiv  Detail & Related papers  (2024-07-05T15:44:53Z)
• Implicit Diffusion Models for Continuous Super-Resolution [65.45848137914592]
  This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution. IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework. The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output.
  arXiv  Detail & Related papers  (2023-03-29T07:02:20Z)
• DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection [80.20339155618612]
  DiffusionAD is a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network.<n>A rapid one-step denoising paradigm achieves hundreds of times acceleration while preserving comparable reconstruction quality.<n>Considering the diversity in the manifestation of anomalies, we propose a norm-guided paradigm to integrate the benefits of multiple noise scales.
  arXiv  Detail & Related papers  (2023-03-15T16:14:06Z)
• Reference-Based Autoencoder for Surface Defect Detection [7.163582730053925]
  We propose a novel unsupervised reference-based autoencoder (RB-AE) to accurately inspect a variety of textured defects. artificial defects and a novel pixel-level discrimination loss function are utilized for training to enable the model to obtain pixel-level discrimination ability.
  arXiv  Detail & Related papers  (2022-11-18T07:13:55Z)
• Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization [67.99082021804145]
  We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss) DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models.
  arXiv  Detail & Related papers  (2022-01-04T08:30:09Z)

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.