Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers

• URL: http://arxiv.org/abs/2303.17505v1
• Date: Wed, 29 Mar 2023 09:13:20 GMT
• Title: Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers
• Abstract summary: Unsupervised anomaly detection (UAD) has been widely implemented in industrial and medical applications. Deep auto-encoder with its variants has demonstrated its advantages in many UAD scenarios. We present LSGS, a method that builds on Vector Quantised-Variational Autoencoder (VQVAE) with a novel aggregated codebook and transformers with global attention.
• Score: 45.34555409340503
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised anomaly detection (UAD) has been widely implemented in industrial and medical applications, which reduces the cost of manual annotation and improves efficiency in disease diagnosis. Recently, deep auto-encoder with its variants has demonstrated its advantages in many UAD scenarios. Training on the normal data, these models are expected to locate anomalies by producing higher reconstruction error for the abnormal areas than the normal ones. However, this assumption does not always hold because of the uncontrollable generalization capability. To solve this problem, we present LSGS, a method that builds on Vector Quantised-Variational Autoencoder (VQVAE) with a novel aggregated codebook and transformers with global attention. In this work, the VQVAE focus on feature extraction and reconstruction of images, and the transformers fit the manifold and locate anomalies in the latent space. Then, leveraging the generated encoding sequences that conform to a normal distribution, we can reconstruct a more accurate image for locating the anomalies. Experiments on various datasets demonstrate the effectiveness of the proposed method.

Related papers

• DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation [52.52576712810738]
  Industrial anomaly detection benefits from anomaly samples, yet newly deployed products typically provide only normal images, making anomaly samples difficult to collect.<n>Existing methods mainly rely on texture images or text descriptions as anomaly sources, which often produce unrealistic anomalies.<n>We propose anomaly transfer-based zero-shot generation, which reuses real anomalies from existing source products.
  arXiv  Detail & Related papers  (2026-09-02T04:03:05Z)
• Mitigating the reconstruction-detection trade-off in VAE-based unsupervised anomaly detection [5.095644632358472]
  We reveal a trade-off between reconstruction quality and anomaly detection among $$-VAE models.<n>Models with constrained latent space reach higher detection metrics but lower reconstruction quality.<n>We investigate two methods to mitigate the reconstructiondetection tradeoff: beta-scheduling and the Sparse VAE.
  arXiv  Detail & Related papers  (2026-04-09T13:00:20Z)
• MLE-UVAD: Minimal Latent Entropy Autoencoder for Fully Unsupervised Video Anomaly Detection [7.322185733864892]
  We propose an entropy-guided autoencoder that detects anomalies through reconstruction error.<n>The key idea is to combine the standard reconstruction loss with a novel Minimal Latent Entropy loss in the autoencoder.<n>Our method achieves robust and superior performance over baselines.
  arXiv  Detail & Related papers  (2026-03-25T02:51:26Z)
• Universal Transformation of One-Class Classifiers for Unsupervised Anomaly Detection [51.73001988341294]
  Anomaly detection is typically formulated as a one-class classification problem.<n>We present a dataset folding method that transforms an arbitrary one-class classifier-based anomaly detector into a fully unsupervised method.
  arXiv  Detail & Related papers  (2026-02-13T16:54:12Z)
• Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection [37.057760207060554]
  Collaborative Reconstruction and Repair (CRR) transforms the reconstruction to repairation.<n>We implement feature-level random masking to ensure that the representations from decoder contain sufficient local information.<n>We train a segmentation network supervised by synthetic anomaly masks, thereby enhancing localization performance.
  arXiv  Detail & Related papers  (2025-12-12T09:24:23Z)
• 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)
• Normality Prior Guided Multi-Semantic Fusion Network for Unsupervised Image Anomaly Detection [7.2755028046583226]
  We propose a novel normality prior guided multi-semantic fusion network for unsupervised anomaly detection.<n>The above multi-semantic features are fused and employed as input to the decoder to guide the reconstruction of anomalies to approximate normality.<n>It achieves the SOTA performance on the MVTec LOCO AD dataset with improvements of 5.7% in pixel-sPRO and 2.6% in image-AUROC.
  arXiv  Detail & Related papers  (2025-06-23T11:54:15Z)
• Anomaly Detection via Autoencoder Composite Features and NCE [1.2891210250935148]
  Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs. We propose a decoupled training approach for anomaly detection that both an AE and a likelihood model trained with noise contrastive estimation (NCE)
  arXiv  Detail & Related papers  (2025-02-04T01:29:22Z)
• GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection [60.78684630040313]
  Diffusion models tend to reconstruct normal counterparts of test images with certain noises added. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. We propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2024-06-11T17:27:23Z)
• Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective [40.21603048003118]
  Variational Autoencoders (VAEs) have gained popularity in recent decades due to their superior de-noising capabilities. FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) Our approach has been evaluated on public datasets and a large-scale cloud system, and the results demonstrate that it outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-05T09:06:57Z)
• Resilient VAE: Unsupervised Anomaly Detection at the SLAC Linac Coherent Light Source [3.7390282036618916]
  This paper introduces the Resilient Variational Autoencoder (ResVAE), a deep generative model specifically designed for anomaly detection. ResVAE exhibits resilience to anomalies present in the training data and provides feature-level anomaly attribution. We apply our proposed method to detect anomalies in the accelerator status at the SLAC Linac Coherent Light Source.
  arXiv  Detail & Related papers  (2023-09-05T15:53:41Z)
• Diversity-Measurable Anomaly Detection [106.07413438216416]
  We propose Diversity-Measurable Anomaly Detection (DMAD) framework to enhance reconstruction diversity. PDM essentially decouples deformation from embedding and makes the final anomaly score more reliable.
  arXiv  Detail & Related papers  (2023-03-09T05:52:42Z)
• Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection [4.772323272202286]
  We propose a two-stream decoder network (TSDN) to learn both normal and abnormal features. We also propose a feature normality estimator (FNE) to eliminate abnormal features and prevent high-quality reconstruction of abnormal regions.
  arXiv  Detail & Related papers  (2023-02-20T06:46:09Z)
• Prototypical Residual Networks for Anomaly Detection and Localization [80.5730594002466]
  We propose a framework called Prototypical Residual Network (PRN) PRN learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. We present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies.
  arXiv  Detail & Related papers  (2022-12-05T05:03:46Z)
• Are we certain it's anomalous? [57.729669157989235]
  Anomaly detection in time series is a complex task since anomalies are rare due to highly non-linear temporal correlations. Here we propose the novel use of Hyperbolic uncertainty for Anomaly Detection (HypAD) HypAD learns self-supervisedly to reconstruct the input signal.
  arXiv  Detail & Related papers  (2022-11-16T21:31:39Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction [4.033624665609417]
  We propose MemAAE, a novel unsupervised anomaly detection method for time-series. By jointly training two complementary proxy tasks, reconstruction and prediction, we show that detecting anomalies via multiple tasks obtains superior performance. MemAAE achieves an overall F1 score of 0.90 on four public datasets, significantly outperforming the best baseline by 0.02.
  arXiv  Detail & Related papers  (2021-10-15T18:29:05Z)
• DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection [9.19194451963411]
  Semi-supervised anomaly detection aims to detect anomalies from normal samples using a model that is trained on normal data. We propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hyper-sphere on its latent representation.
  arXiv  Detail & Related papers  (2021-06-09T21:57:41Z)

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.