Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt

• URL: http://arxiv.org/abs/2505.09264v1
• Date: Wed, 14 May 2025 10:25:14 GMT
• Title: Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
• Authors: Bin-Bin Gao,
• Abstract summary: We propose a simple yet effective method that reconstructs normal features and restores anomaly features with just One Normal Image Prompt (OneNIP)<n>In contrast to previous work, OneNIP allows for the first time to reconstruct or restore anomalies with just one normal image prompt, effectively boosting unified anomaly detection performance.<n>OneNIP outperforms previous methods on three industry anomaly detection benchmarks: MVTec, BTAD, and VisA.
• Score: 4.887838886202545
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Unsupervised reconstruction networks using self-attention transformers have achieved state-of-the-art performance for multi-class (unified) anomaly detection with a single model. However, these self-attention reconstruction models primarily operate on target features, which may result in perfect reconstruction for both normal and anomaly features due to high consistency with context, leading to failure in detecting anomalies. Additionally, these models often produce inaccurate anomaly segmentation due to performing reconstruction in a low spatial resolution latent space. To enable reconstruction models enjoying high efficiency while enhancing their generalization for unified anomaly detection, we propose a simple yet effective method that reconstructs normal features and restores anomaly features with just One Normal Image Prompt (OneNIP). In contrast to previous work, OneNIP allows for the first time to reconstruct or restore anomalies with just one normal image prompt, effectively boosting unified anomaly detection performance. Furthermore, we propose a supervised refiner that regresses reconstruction errors by using both real normal and synthesized anomalous images, which significantly improves pixel-level anomaly segmentation. OneNIP outperforms previous methods on three industry anomaly detection benchmarks: MVTec, BTAD, and VisA. The code and pre-trained models are available at https://github.com/gaobb/OneNIP.

Related papers

• Attention-Guided Perturbation for Unsupervised Image Anomaly Detection [4.084209435209347]
  We present a reconstruction framework named Attention-Guided Perturbation Network (AGPNet)<n>AGPNet learns to add perturbations guided with an attention mask during training.<n>Experiments are conducted on several popular benchmarks covering MVTec-AD, VisA, and MVTec-3D.
  arXiv  Detail & Related papers  (2024-08-14T12:12:43Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• 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)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• FAIR: Frequency-aware Image Restoration for Industrial Visual Anomaly Detection [4.705841907301398]
  Frequency-aware Image Restoration (FAIR) is a novel self-supervised image restoration task that restores images from their high-frequency components. FAIR achieves state-of-the-art performance with higher efficiency on various defect detection datasets.
  arXiv  Detail & Related papers  (2023-09-13T16:28:43Z)
• 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)
• Making Reconstruction-based Method Great Again for Video Anomaly Detection [64.19326819088563]
  Anomaly detection in videos is a significant yet challenging problem. Existing reconstruction-based methods rely on old-fashioned convolutional autoencoders. We propose a new autoencoder model for enhanced consecutive frame reconstruction.
  arXiv  Detail & Related papers  (2023-01-28T01:57:57Z)
• Reconstruction from edge image combined with color and gradient difference for industrial surface anomaly detection [3.42097787126957]
  We propose a new reconstruction network where we reconstruct the original RGB image from its gray value edges (EdgRec) Our method achieves competitive results on the challenging benchmark MVTec AD (97.8% for detection and 97.7% for localization, AUROC.
  arXiv  Detail & Related papers  (2022-10-26T05:21:43Z)
• 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)
• ADTR: Anomaly Detection Transformer with Feature Reconstruction [40.68590890351697]
  Anomaly detection with only prior knowledge from normal samples attracts more attention. Existing CNN-based pixel reconstruction approaches suffer from two concerns. We propose Anomaly Detection TRansformer (ADTR) to apply a transformer to reconstruct pre-trained features.
  arXiv  Detail & Related papers  (2022-09-05T08:01:27Z)
• 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)
• Explainable Deep Few-shot Anomaly Detection with Deviation Networks [123.46611927225963]
  We introduce a novel weakly-supervised anomaly detection framework to train detection models. The proposed approach learns discriminative normality by leveraging the labeled anomalies and a prior probability. Our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings.
  arXiv  Detail & Related papers  (2021-08-01T14:33:17Z)

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.