URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

Wei Luo; Peng Xing; Yunkang Cao; Haiming Yao; Weiming Shen; Zechao Li

cs.CVMar 24, 2026

URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection

Authors: Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao Li

Organizations: State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University, Beijing, China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · State Key Laboratory of Intelligent Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, China

Abstract

Unsupervised anomaly detection plays a pivotal role in industrial defect inspection and medical image analysis, with most methods relying on the reconstruction framework. However, these methods may suffer from over-generalization, enabling them to reconstruct anomalies well, which leads to poor detection performance. To address this issue, instead of focusing solely on normality reconstruction, we propose an innovative Uncertainty-Integrated Anomaly Perception and Restoration Attention Network (URA-Net), which explicitly restores abnormal patterns to their corresponding normality. First, unlike traditional image reconstruction methods, we utilize a pre-trained convolutional neural network to extract multi-level semantic features as the reconstruction target. To assist the URA-Net learning to restore anomalies, we introduce a novel feature-level artificial anomaly synthesis module to generate anomalous samples for training. Subsequently, a novel uncertainty-integrated anomaly perception module based on Bayesian neural networks is introduced to learn the distributions of anomalous and normal features. This facilitates the estimation of anomalous regions and ambiguous boundaries, laying the foundation for subsequent anomaly restoration. Then, we propose a novel restoration attention mechanism that leverages global normal semantic information to restore detected anomalous regions, thereby obtaining defect-free restored features. Finally, we employ residual maps between input features and restored features for anomaly detection and localization. The comprehensive experimental results on two industrial datasets, MVTec AD and BTAD, along with a medical image dataset, OCT-2017, unequivocally demonstrate the effectiveness and superiority of the proposed method.

Figures & tables

Fig. 1: Comparison of different unsupervised anomaly detection methods. (a) DRAEM [ 1 ] . (b) MemAE [ 2 ] . (c) The proposed method (URA-Net). URA-Net employs the U-I (Uncertainty-Integrated) Anomaly Perception module to roughly estimate anomalous regions ( Mean ) and ambiguous boundaries ( Uncertainty ). Subsequently, The Restoration Attention module utilizes global normal semantic information to restore the detected anomalies, ultimately resulting in defect-free restored images. It is noteworthy that our proposed method relies on feature reconstruction. The reconstructed images are generated by training a decoder, which is exclusively employed for visualization.

Fig. 2: Overall architecture of our URA-Net. It primarily consists of three modules: feature-level artificial anomaly synthesis module (FASM), uncertainty-integrated anomaly perception module (UIAPM), and restoration attention module (RAM). First, a pre-trained backbone is employed to transform input images into multi-level features. FASM is utilized to generate artificial anomalies at the feature level for training. Subsequently, UIAPM roughly estimates anomalous regions ( Mean ) and ambiguous boundaries ( Uncertainty ). Then RAM leverages global normal semantic information to restore detected anomalous regions and ambiguous boundaries, yielding defect-free restored features. Finally, the residuals between input features and restored ones are utilized for anomaly detection and localization.

Fig. 3: Synthesis process for feature-level artificial anomalies.

Fig. 4: Illustration of uncertainty-integrated anomaly perception module (UIAPM). UIAPM works as a probabilistic model to roughly estimate anomalous regions and ambiguous boundaries.

Fig. 5: The effectiveness of UIAPM in anomaly perception. From left to right are: anomalous image, ground truth, mean map $U$ , uncertainty map $V$ , mask $M_{U}$ generated by $U$ , and the final mask $M_{final}$ combined with uncertainty.

Fig. 6: (a) The proposed restoration transformer block consists of three components: layer normalization (LN), restoration attention module (RAM) , and multi-layer perceptron (MLP). (b) The RAM architecture. RAM leverages global normal semantic information to restore anomalous features.

Taxonomy

Embedding-Based

Image Reconstruction

Feature Reconstruction

Method

\rightarrow

PaDiM

PFM

PatchCore

CDO †

ADPS

RIAD

DRAEM

OCR-GAN

UTRAD

RD4AD

FOD †

Venue

\rightarrow

ICPR’21

TII’22

CVPR’22

TII’23

TNNLS’24

PR’21

ICCV’21

TIP’23

NN’22

CVPR’22

ICCV’23

URA-Net

Category

\downarrow

[ 57 ]

[ 36 ]

[ 37 ]

[ 20 ]

[ 58 ]

[ 23 ]

[ 1 ]

[ 59 ]

[ 40 ]

[ 60 ]

[ 42 ]

Texture

Carpet

99.8 /99.1

100 /99.2

98.7/99.0

99.5/99.0

97.4/ 99.5

84.2/94.2

97.0/95.5

99.4/-

96.3/97.3

98.9/98.9

100 /99.2

99.8 / 99.3

Grid

96.7/97.3

98.0/98.8

98.2/98.7

99.9 /99.2

100 /99.2

99.6/96.3

99.9 / 99.7

99.6/-

98.7/97.6

100 / 99.3

100 /98.7

100 /99.0

Leather

100 /99.2

100 / 99.4

100 /98.3

100 /99.1

100 / 99.9

100 / 99.4

100 /98.6

97.1 /-

100 /98.6

100 / 99.4

100 /99.3

100 / 99.4

TABLE I: Anomaly detection and localization results in terms of image/pixel level AUROC on MVTec AD dataset [ 3 ] . The best result is in bold , and the second best is underlined .

{\dagger}

denotes the results obtained through our implementation.

Fig. 7: The localization results of the proposed URA-Net and comparative methods on the MVTec AD dataset [ 3 ] . Our proposed model accurately localizes anomaly regions across various categories.

Method $\rightarrow$	PaDiM	VT-ADL	FastFlow	MKD	PFM †	PatchCore	DRAEM	UTRAD †	RD4AD †	FOD †
Venue $\rightarrow$	ICPR’21	ISIE’2021	Arxiv’21	CVPR’21	TII’22	CVPR’22	ICCV’21	NN’22	CVPR’22	ICCV’23	URA-Net
Category $\downarrow$	[ 57 ]	[ 31 ]	[ 61 ]	[ 62 ]	[ 36 ]	[ 37 ]	[ 1 ]	[ 40 ]	[ 60 ]	[ 42 ]
Product 01	99.8 /97.0	97.6/ 99.0	99.4/97.1	93.8/94.9	92.9/95.0	98.4/ 97.3	99.5/92.7	97.7/93.8	98.4/96.3	99.6/97.2	99.9 /97.0
Product 02	82.0/96.0	71.0/94.0	82.4/93.6	88.2 /96.3	80.0/ 96.7	81.8/96.1	77.4/93.6	76.8/95.5	86.5/ 96.6	86.7/95.7	88.1 /96.2
Product 03	99.4/98.8	82.6/77.0	91.1/98.3	98.5/98.3	99.6/ 99.6	100 /99.3	99.8 /96.4	99.7/99.4	99.7/99.7	100 / 99.6	100 / 99.7
Mean	93.7/97.3	83.7/90.0	90.1/96.3	93.5/96.5	90.8/97.1	93.4/ 97.6	92.2/94.2	91.4/96.2	94.9/ 97.5	95.4 / 97.5	96.0 / 97.6

TABLE II: Anomaly detection and localization results in terms of image/pixel level AUROC on BTAD dataset [ 31 ] . The best result is in bold , and the second best is underlined .

{\dagger}

denotes the results obtained through our implementation.

Method $\rightarrow$	AE	Ganomaly	f-AnoGAN	SALAD	ProxyAno	SSD	STPFM	MKD	PaDiM	RD4AD	AE-flow
Venue $\rightarrow$	Arxiv’18	ACCV’18	MIA’21	TMI’21	TMI’21	ICLR’21	BMVC’21	CVPR’21	ICPR’21	CVPR’22	ICLR’23	URA-Net
Metric $\downarrow$	[ 63 ]	[ 64 ]	[ 65 ]	[ 66 ]	[ 67 ]	[ 68 ]	[ 69 ]	[ 62 ]	[ 57 ]	[ 60 ]	[ 70 ]
AUROC	77.8	83.5	83.4	96.4	93.3	92.3	96.9	96.7	96.9	97.6	98.1	98.6
F1-score	85.8	88.7	84.7	93.4	72.5	91.9	95.8	94.6	95.2	96.4	96.4	97.1
ACC	78.3	81.6	77.5	90.6	84.9	87.2	93.7	91.6	92.8	94.6	94.4	95.7

TABLE III: Anomaly detection results in terms of image level AUROC on OCT-2017 dataset [ 32 ] . The best result is in bold , and the second best is underlined .

Fig. 8: The localization results of the proposed URA-Net on the BTAD benchmark [ 31 ] .

Variant	IASM	FASM	UIAPM	RAM	w/o SK	I-AUROC	P-AUROC	FPS	Parameters	FLOPs
A	✘	✘	✘	✘	✘	97.6	97.3	63.25	97285184	30598758400
B	✔	✘	✘	✘	✘	98.2 +0.6 $\uparrow$	97.8 +0.5 $\uparrow$	63.25	97285184	30598758400
C	✘	✔	✘	✘	✘	98.4 +0.8 $\uparrow$	97.9 +0.6 $\uparrow$	63.25	97285184	30598758400
D	✘	✔	✔	✘	✘	98.8 +1.2 $\uparrow$	98.1 +0.8 $\uparrow$	57.11	97286722	30599151616
E	✘	✔	✔	✔	✘	99.2 +1.6 $\uparrow$	98.4 +1.1 $\uparrow$	55.10	97286746	30599151616
F	✘	✔	✔	✔	✔	99.4 +1.8 $\uparrow$	98.5 +1.2 $\uparrow$	55.10	97286746	30599151616

TABLE IV: Ablation analysis on the MVTec AD dataset [ 3 ] . IASM refers to image-level artificial anomaly synthesis module. ‘ w/o SK ’ indicates that removing skip-connection.

Fig. 9: The localization results of the proposed URA-Net on the OCT-2017 medical dataset [ 32 ] .

Fig. 10: Frames per second (FPS) versus image-wise AUROC on MVTec AD benchmark [ 3 ] . The size of the circles represents the number of parameters. The floating point operations (FLOPs) are also reported. (

\cdot

\cdot

) represents (FPS, Image AUROC).

Fig. 11: Visualization of the impact of UIAPM . We plot the t-SNE visualization of normal and abnormal instances for Bottle and Hazelnut categories in MVTec AD [ 3 ] dataset.

Fig. 12: Visualization of the impact of RAM . (a) Input anomalous image and corresponding label. (b) Reconstruction result without RAM . (c) Reconstruction result with RAM . It is noteworthy that our proposed method relies on feature reconstruction. The reconstructed images are generated by training a decoder, which is exclusively employed for visualization.

Fig. 13: Localization results under different noise levels . From top to bottom are the input noisy images and the corresponding detection results, respectively.

Fig. 14: Comparison of attention map visualizations between the self-attention module (SAM) and the proposed RAM . (a) Anomalous image, where each red rectangle represents an anomalous patch. (b) Corresponding label. (c) Attention map generated by the SAM. (d) Attention map generated by the proposed RAM.

Fig. 15: Analysis of failure case of the proposed method.

Explore similar work

A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection
Mar 24, 2026Wei Luo, Haiming Yao, Zhenfeng Qiang +2Unsupervised Anomaly Detection Anomaly Detection
State Key Laboratory of Precision Measurement Technology and Instruments, Tsinghua University, Beijing, 100084, China · School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China
SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection
Jul 16, 2026Huong Ninh, Chien Thai, Mai Xuan Trang +3Anomaly Localization Reconstruction-Based Anomaly Detection
Institute of Artificial Intelligence, University of Engineering and Technology, Vietnam National University · Applied AI Lab, Phenikaa School of Computing, Phenikaa University
Statistical Non-linear Reconstruction Loss for Image Anomaly Detection
Jul 14, 2026Nguyen Minh Tri, Hoang Khuong Duy, Huynh Cong Viet NguIndustrial Anomaly Detection Anomaly Localization
AIC-Lab, FPT University

Mar 24, 2026J/K move · Enter open · S save

A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection

Wei Luo, Haiming Yao, Zhenfeng Qiang, Xiaotian Zhang+1

State Key Laboratory of Precision Measurement Technology and Instruments, Tsinghua University, Beijing, 100084, China · School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China

Unsupervised Anomaly Detection Anomaly Detection Reconstruction-Based Anomaly Detection Industrial Anomaly Detection

Open paper AskPDF arXiv

Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal and anomalous regions can be well reconstructed and fail to identify outliers. The severity of this problem increases with the complexity of the normal data distribution. Consequently, existing methods may exhibit excellent detection performance in a specific scenario, but their performance sharply declines when transferred to another scenario. This paper focuses on establishing a universal model applicable to anomaly detection tasks across different settings, termed as universal anomaly detection. In this work, we introduce a novel, straightforward yet efficient framework for universal anomaly detection: \uline{F}eature \uline{S}huffling and \uline{R}estoration (FSR), which can alleviate the identical shortcut issue across different settings. First and foremost, FSR employs multi-scale features with rich semantic information as reconstruction targets, rather than raw image pixels. Subsequently, these multi-scale features are partitioned into non-overlapping feature blocks, which are randomly shuffled and then restored to their original state using a restoration network. This simple paradigm encourages the model to focus more on global contextual information. Additionally, we introduce a novel concept, the shuffling rate, to regulate the complexity of the FSR task, thereby alleviating the identical shortcut across different settings. Furthermore, we provide theoretical explanations for the effectiveness of FSR framework from two perspectives: network structure and mutual information. Extensive experimental results validate the superiority and efficiency of the FSR framework across different settings.Code is available at https://github.com/luow23/FSR.

Abstract

Explore similar work

A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection

SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection

Statistical Non-linear Reconstruction Loss for Image Anomaly Detection