A Unified Model for Multi-Class Anomaly Detection
Open accessThe DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index; 14 of the 27 sources its claims cite were checked for support.
Abstract
Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects. In this work, we present UniAD that accomplishes anomaly detection for multiple classes with a unified framework. Under such a challenging setting, popular reconstruction networks may fall into an 'identical shortcut', where both normal and anomalous samples can be well recovered, and hence fail to spot outliers. To tackle this obstacle, we make three improvements, including a layer-wise query decoder to help model the multi-class distribution. When learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88.1% to 96.5%) and anomaly localization (from 89.5% to 96.8%).
Overview
CoChat Summary
TL;DR
UniAD is a unified feature-reconstruction framework for multi-class anomaly detection that avoids the “identical shortcut” via a layer-wise query decoder, neighbor masked attention, and feature jittering. On MVTec-AD’s 15-category unified setting it reaches 96.5% AUROC for anomaly detection and 96.8% for localization, substantially outperforming prior methods.
Key findings
- On MVTec-AD with one unified model for 15 categories, UniAD achieves 96.5% AUROC for anomaly detection versus 88.1% for the second competitor DRAEM, and 96.8% for anomaly localization versus 89.5% for the second competitor PaDiM.
- On CIFAR-10 under the proposed many-versus-many unified setting, UniAD reaches 87.2% mean AUROC, outperforming FCDD+OE by 8.3% without auxiliary outlier exposure; baselines US and FCDD fall to 55.9% and 55.8% mean AUROC.
- Ablations show the query embedding is critical: without query embedding, detection/localization AUROC is 69.5%/79.4%; with one query embedding it rises to 87.6%/92.8%; with layer-wise query it reaches 95.0%/96.5%; combining layer-wise query, neighbor masked attention, and feature jittering gives 96.5%/96.8%.
- Transformer-based competitors under the unified setting perform far worse: InTra 65.3%/70.6%, VT-ADL 55.4%/64.4%, AnoViT 69.6%/68.4%, while a UniAD baseline with one query embedding already reaches 87.6%/92.8%.
Methods
- UniAD reconstructs features from a fixed ImageNet-pretrained EfficientNet-b4 backbone: stage-1 to stage-4 features are resized, concatenated into a 272-channel map, tokenized, and linearly projected to 256 channels; the model uses a Neighbor Masked Encoder and Layer-wise Query Decoder, with neighbor masked attention masking each token’s self and neighbors, and feature jittering adding Gaussian noise to input tokens.
- Training on MVTec-AD uses 224×224 images, 14×14 feature size, 1000 epochs on 8 NVIDIA Tesla V100 16GB GPUs, batch size 64, AdamW with weight decay 1×10⁻⁴, initial learning rate 1×10⁻⁴ dropped by 0.1 after 800 epochs, 4 encoder and 4 decoder layers, neighbor size 7×7, jittering scale 20, jittering probability 1, and 5 random seeds; CIFAR-10 uses stage-1 to stage-5 features forming a 720-channel map and batch size 128.
- The objective is MSE feature reconstruction loss; anomaly localization scores are the L2 norm of reconstruction differences, upsampled to image size, and image-level anomaly detection takes the maximum of the average-pooled score map; evaluation uses AUROC under the unified case without fine-tuning.
Limitations
- Stated in the paper: the method does not use category labels, and incorporating labels into the unified model should be further studied; practical normal samples are not as consistent as MVTec-AD, though UniAD handles all 15 MVTec-AD categories; anomaly detection for video surveillance may infringe personal privacy.
- Evident from the text: evaluation is limited to MVTec-AD and CIFAR-10, with no real-world video-surveillance experiments despite the privacy discussion; the unified setting assumes class labels are inaccessible at both training and inference, so the method cannot exploit category information that might improve multi-class modeling.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 5 Not valid · 6 Not checked · 95 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Despite the rapid advance of unsupervised anomaly detection, existing methods require to train separate models for different objects.”
- Also stated in: § 1 Introduction · p. 1 · plain
“existing methods [6, 11, 26, 28, 49, 50, 53] propose to train separate models for different classes of objects”
What the sources say
- Could not verifycites [6] [6] P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In IEEE Conf. Comput. Vis. Pattern Recog. , 2020. - sourceExperimental — accuracy not yet measured
Our copy repeatedly characterises the shortcomings of existing unsupervised anomaly detection methods, but never in terms of needing a separate model per object class: the Introduction (p. 1) blames 'shallow machine learning pipelines that require a dimensionality reduction of the used feature space' and 'heavy training data subsampling', Related Work (p. 2) and Sec. 2.1 (p. 2) blame from-scratch generative models, per-pixel reconstruction errors and patch-sampled shallow classifiers, and the Introduction (p. 1) notes that one-/multi-class methods 'assume that anomalies manifest themselves in the form of images of an entirely different class'. Searches for 'separate model per object/class', 'single model for all categories' and per-category training returned no passage making the attributed point; conversely the paper itself trains on 'a single class of anomaly-free images' and fits models per MVTec AD category (Sec. 4.2, p. 7), so nothing in our copy states or contradicts the claim that existing methods require object-specific models. (LLM, conf=0.70)
- Partly supportedcites [11] [11] T. Defard, A. Setkov, A. Loesch, and R. Audigier. PaDim: A patch distribution modeling framework for anomaly detection and localization. In Int. Conf. Pattern Recog. , 2021. - sourceExperimental — accuracy not yet measured
The Experimental setups section (p. 4) says the paper's VAE baseline is trained on each MVTec AD class, supporting class-specific training as an example. But the Scalability gain section (p. 6) says SPADE requires no training, so the paper does not support the broader claim that existing methods generally require separate models for different objects. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [26] [26] C.-L. Li, K. Sohn, J. Yoon, and T. Pfister. CutPaste: Self-supervised learning for anomaly detection and localization. In IEEE Conf. Comput. Vis. Pattern Recog. , 2021. - source
- Partly supportedcites [28] [28] P. Liznerski, L. Ruff, R. A. Vandermeulen, B. J. Franks, M. Kloft, and K.-R. Müller. Explainable deep one-class classification. In Int. Conf. Learn. Represent. , 2021. - sourceExperimental — accuracy not yet measured
Section 4.1 (p. 5) describes a common one-vs-rest anomaly-detection benchmark that treats each class in turn as nominal, consistent with training class-specific models. It does not establish that existing unsupervised anomaly-detection methods generally require a separate model for every object class. (LLM, conf=0.84)
- Not checked — no full text of the sourcecites [49] [49] J. Yi and S. Yoon. Patch SVDD: Patch-level SVDD for anomaly detection and segmentation. In Asian Conf. Comput. Vis. , 2020. - source
- Partly supportedcites [50] [50] Z. You, K. Yang, W. Luo, L. Cui, Y. Zheng, and X. Le. ADTR: Anomaly detection transformer with feature reconstruction. arXiv preprint arXiv:2209.01816 , 2022. - sourceExperimental — accuracy not yet measured
The Dataset section (p. 6) describes a one-class CIFAR-10 setup in which the training set of one class is used for training, supporting class-specific training in that setting. The paper does not establish that existing unsupervised anomaly detection methods generally require separate models for different objects. (LLM, conf=0.75)
- Not checked — no full text of the sourcecites [53] [53] V. Zavrtanik, M. Kristan, and D. Skoˇ caj. DRAEM-A discriminatively trained reconstruction embedding for surface anomaly detection. In Int. Conf. Comput. Vis. , 2021. - source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 1 Introduction · p. 1 · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“EfficientNet performs obviously better than ResNet, especially in anomaly detection.”
What the sources say
- Not checked — no full text of the sourcecites [20] [20] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In IEEE Conf. Comput. Vis. Pattern Recog. , 2016. - source
- Partly supportedcites [41] [41] M. Tan and Q. Le. EfficientNet: Rethinking model scaling for convolutional neural networks. In Int. Conf. Mach. Learn. , 2019. - sourceExperimental — accuracy not yet measured
The Introduction (p. 2) reports higher ImageNet accuracy for EfficientNet-B4 than ResNet-50, and the transfer-learning discussion (p. 8) reports better accuracy–parameter performance than ResNet. The paper does not report an anomaly-detection comparison, so it does not support the claim that EfficientNet performs especially better in that task. (LLM, conf=0.90)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Every source the paper cites for this claim was checked and supports it.
In the paper
“Adding only one query embedding to the first decoder layer ( i.e. , vanilla transformer [43]) promotes the performance dramatically by 18.1% and 13.4% in anomaly detection and localization, respectively.”
What the sources say
- Supportedcites [43] [43] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. In Adv. Neural Inform. Process. Syst. , 2017. - source
The citation is attached to “vanilla transformer,” identifying the architecture used as a baseline, rather than to the reported performance gains. The Introduction (p. 2) proposes the Transformer, and Section 3.1 (p. 3) describes its decoder layers. The 18.1% and 13.4% results are not attributed to this source by that citation. (LLM, conf=0.92)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Inspired by Denoising Auto-Encoder (DAE) [3, 44], we add perturbations to feature tokens, guiding the model to learn knowledge of normal samples by the denoising task.”
What the sources say
- Supportedcites [3] [3] Y. Bengio, L. Yao, G. Alain, and P. Vincent. Generalized denoising auto-encoders as generative models. In Adv. Neural Inform. Process. Syst. , 2013. - source
The Introduction describes corrupting observed inputs and training a denoising auto-encoder to reconstruct them. The Conclusion says denoising training implicitly estimates the underlying data-generating process. The citing authors present perturbing feature tokens as their own DAE-inspired implementation, not as a procedure used in this source. (LLM, conf=0.90)
- Not checked — no full text of the sourcecites [44] [44] P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol. Extracting and composing robust features with denoising autoencoders. In Int. Conf. Mach. Learn. , 2008. - source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“NMA together with FJ provides a quite strong performance (96.2% for detection and 96.6% for localization).”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
72 more claims
Create a free account to see all 114 claims and every source verdict.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 14
- The quote only partly states this claim. 2
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 4
- [10][10] L. Deecke, L. Ruff, R. A. Vandermeulen, and H. Bilen. Transfer-based semantic anomaly detection. In Int. Conf. Mach. Learn. , 2021. -
- [22][22] L. Ilya and H. Frank. Decoupled weight decay regularization. In Int. Conf. Learn. Represent. , 2019. -
- [24][24] A. Krizhevsky. Learning multiple layers of features from tiny images. Master's thesis, University of Tront , 2009. -
- [36][36] L. Ruff, R. Vandermeulen, N. Goernitz, L. Deecke, S. A. Siddiqui, A. Binder, E. Müller, and M. Kloft. Deep one-class classification. In Int. Conf. Mach. Learn. , 2018. -
Cited by
Deep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., & Wang, J. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i3.27963 · Cited by 298
A Diffusion-Based Framework for Multi-Class Anomaly Detection
He, H., Zhang, J., Chen, H., Chen, X., Li, Z., Chen, X., Wang, Y., Wang, C., & Xie, L. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i8.28690 · Cited by 212
RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
Zhang, X., Xu, M., & Zhou, X. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01580 · Cited by 209
Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection
Wang, C., Zhu, W., Gao, B.-B., Gan, Z., Zhang, J., Gu, Z., Qian, S., Chen, M., & Ma, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02159 · Cited by 359
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
Guo, J., Lu, S., Zhang, W., Chen, F., Li, H., & Liao, H. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01900 · Cited by 307
LAnoBERT: System log anomaly detection based on BERT masked language model
Lee, Y., Kim, J., & Kang, P. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110689 · Cited by 191
Zhang, Z., Zhao, Z., Zhang, X., Sun, C., & Chen, X. (2023) · Computers in Industry · doi:10.1016/j.compind.2023.103990 · Cited by 165
IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing
Xie, G., Wang, J., Liu, J., Lyu, J., Liu, Y., Wang, C., Zheng, F., & Jin, Y. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3357213 · Cited by 163
Chen, Q., Luo, H., Lv, C., & Zhang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72855-6_3 · Cited by 230
CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-Shot Anomaly Detection
Chen, X., Zhang, J., Tian, G., He, H., Zhang, W., Wang, Y., Wang, C., & Liu, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-9003-6_2 · Cited by 167
Exploring plain ViT features for multi-class unsupervised visual anomaly detection
Zhang, J., Chen, X., Wang, Y., Wang, C., Liu, Y., Li, X., Yang, M., & Tao, D. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104308 · Cited by 135
OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization
Zhao, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00382 · Cited by 166
EasyNet: An Easy Network for 3D Industrial Anomaly Detection
Chen, R., Xie, G., Liu, J., Wang, J., Luo, Z., Wang, J., & Zheng, F. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611876 · Cited by 136
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
Gu, Z., Zhu, B., Zhu, G., Chen, Y., Li, H., Tang, M., & Wang, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680685 · Cited by 136
MedIAnomaly: A comparative study of anomaly detection in medical images
Cai, Y., Zhang, W., Chen, H., & Cheng, K.-T. T. (2025) · Medical Image Analysis · doi:10.1016/j.media.2025.103500 · Cited by 111
Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
Yang, Y., Lee, K., Dariush, B., Cao, Y., & Lo, S.-Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73004-7_18 · Cited by 146
Simple and effective Frequency-aware Image Restoration for industrial visual anomaly detection
Liu, T., Li, B., Du, X., Jiang, B., Geng, L., Wang, F., & Zhao, Z. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.103064 · Cited by 83
Removing Anomalies as Noises for Industrial Defect Localization
Lu, F., Yao, X., Fu, C., & Jia, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01481 · Cited by 88
Anomaly Detection for Medical Images Using Heterogeneous Auto-Encoder
Lu, S., Zhang, W., Zhao, H., Liu, H., Wang, N., & Li, H. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3381435 · Cited by 78
A survey on RGB, 3D, and multimodal approaches for unsupervised industrial image anomaly detection
Lin, Y., Chang, Y., Tong, X., Yu, J., Liotta, A., Huang, G., Song, W., Zeng, D., Wu, Z., Wang, Y., et al. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103139 · Cited by 86
Prior Normality Prompt Transformer for Multiclass Industrial Image Anomaly Detection
Yao, H., Cao, Y., Luo, W., Zhang, W., Yu, W., & Shen, W. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3413322 · Cited by 67
Template-guided Hierarchical Feature Restoration for Anomaly Detection
Guo, H., Ren, L., Fu, J., Wang, Y., Zhang, Z., Lan, C., Wang, H., & Hou, X. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00593 · Cited by 89
AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization
Luo, W., Yao, H., Yu, W., & Li, Z. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3368142 · Cited by 72
Real3D-AD: A Dataset of Point Cloud Anomaly Detection
Liu, J., Xie, G., Chen, R., Li, X., Wang, J., Liu, Y., Wang, C., & Zheng, F. (2023) · neural information processing systems · doi:10.52202/075280-1324 · Cited by 175
Encoder-Decoder Contrast for Unsupervised Anomaly Detection in Medical Images
Guo, J., Lu, S., Jia, L., Zhang, W., & Li, H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3327720 · Cited by 68
Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt
Liu, J., Wu, K., Nie, Q., Chen, Y., Gao, B.-B., Liu, Y., Wang, J., Wang, C., & Zheng, F. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i4.28153 · Cited by 98
A Discrepancy Aware Framework for Robust Anomaly Detection
Cai, Y., Liang, D., Luo, D., He, X., Yang, X. Y., & Bai, X. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3318302 · Cited by 59
Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
Zhu, J., Cai, S., Deng, F. Y., Ooi, B. C., & Wu, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681190 · Cited by 85
MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection
Bao, T., Chen, J., Li, W., Wang, X., Fei, J., Wu, L., Zhao, R. J., & Ye, Z. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00106 · Cited by 58
Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection
Chen, Q., Luo, H., Gao, H., Lv, C., & Zhang, Z. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3479887 · Cited by 67
Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detection
Yao, X., Li, R., Qian, Z., Luo, Y., & Zhang, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00626 · Cited by 71
GPT-4V-AD: Exploring Grounding Potential of VQA-Oriented GPT-4V for Zero-Shot Anomaly Detection
Zhang, J., He, H., Chen, X., Xue, Z., Wang, Y., Wang, C., Xie, L., & Liu, Y. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-9003-6_1 · Cited by 51
Normal Image Guided Segmentation Framework for Unsupervised Anomaly Detection
Xing, P., Sun, Y., Zeng, D., & Li, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3327448 · Cited by 39
Liu, H., Su, X., Shen, X., & Zhou, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3411009 · Cited by 53
A 2 C: A modular multi-stage collaborative decision framework for human–AI teams
Tariq, S., Chhetri, M. B., Nepal, ., & Paris, C. L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127318 · Cited by 48
Deep learning-based anomaly detection for precision field crop protection
Cheng, W., Shan, Y., & Zhen, M. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1576756 · Cited by 36
Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection
He, L., Jiang, Z., Peng, J., Zhu, W., Liu, L., Du, Q., Hu, X., Chi, M., Wang, Y., & Wang, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72855-6_13 · Cited by 59
PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Zhou, Q., Li, W., Jiang, L., Wang, G., Zhou, G., Zhang, S., & Zhao, H. (2023) · neural information processing systems · doi:10.52202/075280-1930 · Cited by 73
FR-PatchCore: An Industrial Anomaly Detection Method for Improving Generalization
Jiang, Z., Zhang, Y., Wang, Y., Li, J., & Gao, X. (2024) · Sensors · doi:10.3390/s24051368 · Cited by 41
Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection
Yao, X., Li, R., Qian, Z., Wang, L., & Zhang, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73411-3_6 · Cited by 56
Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
Gui, G., Gao, B.-B., Liu, J., Wang, C., & Wu, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73010-8_13 · Cited by 60
An Incremental Unified Framework for Small Defect Inspection
Tang, J., Lu, H., Xu, X., Wu, R., Hu, S., Zhang, T., Cheng, T. W., Ge, M., Chen, Y.-C., & Tsung, F. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72751-1_18 · Cited by 57
Cheng, Y., Cao, Y., Wang, D., Shen, W., & Li, W. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3544462 · Cited by 48
MSTAD: A masked subspace-like transformer for multi-class anomaly detection
Kang, B., Zhong, Y., Sun, Z., Deng, L., Wang, M., & Zhang, J. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.111186 · Cited by 31
Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection
Dai, S., Wu, Y., Li, X., & Xue, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i2.27910 · Cited by 41
Continuous Memory Representation for Anomaly Detection
Lee, J. C., Kim, T., Park, E., Woo, S. S., & Ko, J. H. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72983-6_25 · Cited by 41
Foundation models and Transformers for anomaly detection: A survey
Ammar, M. B., Mendoza, A., Belkhir, N., Manzanera, A., & Franchi, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103517 · Cited by 36
Zhao, Q., Wang, Y., Wang, B., Lin, J., Yan, S., Song, W., Liotta, A., Yu, J., Gao, S., & Zhang, W. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3341259 · Cited by 26
Mixed-Attention Auto Encoder for Multi-Class Industrial Anomaly Detection
Liu, J., & Wang, F. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446794 · Cited by 26
Scalable Industrial Visual Anomaly Detection With Partial Semantics Aggregation Vision Transformer
Yao, H., Luo, W., Lou, J., Yu, W., Zhang, X., Qiang, Z., & Shi, H. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3343832 · Cited by 31
Learning a Cross-Modality Anomaly Detector for Remote Sensing Imagery
Li, J., Wang, X., Zhao, H., & Zhong, Y. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3490894 · Cited by 27
Unsupervised anomaly detection and localization with one model for all category
Tan, P., & Wong, W. K. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111533 · Cited by 26
Reverse Knowledge Distillation with Two Teachers for Industrial Defect Detection
Pei, M., Liu, N., Gao, P., & Sun, H. (2023) · Applied Sciences · doi:10.3390/app13063838 · Cited by 21
No, G., Lee, Y., Kang, H., & Kang, P. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108613 · Cited by 24
Long-Tailed Anomaly Detection with Learnable Class Names
Ho, C.-H., Peng, K., & Vasconcelos, N. M. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01182 · Cited by 38
Shangguan, W., Wu, H., Niu, Y., Yin, H., Yu, J., Chen, B., & Huang, B. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103240 · Cited by 24
Dual-path Frequency Discriminators for few-shot anomaly detection
Bai, Y., Zhang, J., Chen, Z., Dong, Y., Cao, Y., & Tian, G. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112397 · Cited by 22
ADPS: Asymmetric Distillation Postsegmentation for Image Anomaly Detection
Xing, P., Tang, H., Tang, J., & Li, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3390806 · Cited by 26
Anomaly detection in medical via multimodal foundation models
Tang, Z. J., Tang, Z. J., & Wu, J. (2025) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2025.1644697 · Cited by 25
Curved Geometric Networks for Visual Anomaly Recognition
Hong, J., Fang, P., Li, W., Han, J., Petersson, L., & Harandi, M. T. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3309846 · Cited by 28
Yao, H., Luo, W., Zhang, W., Zhang, X., Qiang, Z., & Luo, D. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109235 · Cited by 19
MoEAD: A Parameter-Efficient Model for Multi-class Anomaly Detection
Meng, S., Meng, W., Zhou, Q., Li, S., Hou, W., & He, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73013-9_20 · Cited by 44
ResAD: A Simple Framework for Class Generalizable Anomaly Detection
Yao, X., Chen, Z., Gao, C., Zhai, G., & Zhang, C. (2024) · neural information processing systems · doi:10.52202/079017-3979 · Cited by 52
Semantic-aware normalizing flow with feature fusion for image anomaly detection
Ma, W., Li, Y., Lan, S., Wang, W., Huang, W., & Zhu, W. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127728 · Cited by 20
Produce Once, Utilize Twice for Anomaly Detection
Wang, S., Li, Q., Luo, H., Lv, C., & Zhang, Z. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3420775 · Cited by 19
Adapting the segment anything model for multi-modal retinal anomaly detection and localization
Li, J., Chen, T., Wang, X., Zhong, Y., & Xiao, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102631 · Cited by 27
Context-aware feature reconstruction for class-incremental anomaly detection and localization
Pang, J., & Li, C. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106788 · Cited by 17
Take an Irregular Route: Enhance the Decoder of Time-Series Forecasting Transformer
Shen, L., Wei, Y., Wang, Y., & Qiu, H. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3341099 · Cited by 16
Learning to Detect Multi-class Anomalies with Just One Normal Image Prompt
Gao, B.-B. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72855-6_26 · Cited by 43
AnoOnly: Semi-supervised anomaly detection with the only loss on anomalies
Zhou, Y., Yang, P., Qu, Y., Xu, X., Sun, Z., & Cichocki, A. S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125597 · Cited by 15
Deep feature clustering for multi-class industrial image anomaly detection
Wang, R., Li, Z., Zheng, L., Wang, W., & Li, S. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113134 · Cited by 21
DMU-TransNet: Dense multi-scale U-shape transformer network for anomaly detection
Zhou, W., Wu, S., Wang, Y., Zuo, L., Yi, Y., & Cui, W. (2024) · Measurement · doi:10.1016/j.measurement.2024.114216 · Cited by 14
Unified Model Based on Reinforced Feature Reconstruction for Metro Track Anomaly Detection
Duan, M., Mao, L., Liu, R., Liu, W., & Liu, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3348118 · Cited by 13
PixOOD: Pixel-Level Out-of-Distribution Detection
Vojíř, T., Šochman, J., & Matas, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73027-6_6 · Cited by 27
UniFormaly: Towards task-agnostic unified framework for visual anomaly detection
Lee, Y., Lim, H., Jang, S., & Yoon, H. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111820 · Cited by 20
FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation
Gong, T., Chu, Q., Liu, B., Zhou, W., & Yu, N. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01971 · Cited by 26
That’s BAD: blind anomaly detection by implicit local feature clustering
Zhang, J., Suganuma, M., & Okatani, T. (2024) · Machine Vision and Applications · doi:10.1007/s00138-024-01511-9 · Cited by 12
Liu, H., & Sun, J. Z. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3507097 · Cited by 13
Hard-Normal Example-Aware Template Mutual Matching for Industrial Anomaly Detection
Chen, Z., Xie, X., Yang, L., & Lai, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02323-0 · Cited by 17
Kohler, M., Mitsios, D., & Endisch, C. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.12.005 · Cited by 12
Multi-View Attention Guided Feature Learning for Unsupervised Surface Defect Detection
Zhou, J., Liu, M., Ma, Y., Jiang, S., & Wang, Y. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3566311 · Cited by 13
Integrating local and global correlations with Mamba-Transformer for multi-class anomaly detection
Ma, Z., Li, J., Jiang, K., & Wong, W. K. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113740 · Cited by 16
UniFlow: Unified Normalizing Flow for Unsupervised Multi-Class Anomaly Detection
Zhong, J., & Song, Y. (2024) · Information · doi:10.3390/info15120791 · Cited by 12
Coarse-to-fine vision-based welding spot anomaly detection in production lines of body-in-white
Liu, W., Hu, J., & Qi, J. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.05.003 · Cited by 13
Li, Z., Ge, Y., & Meng, L. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103356 · Cited by 13
Liu, T., Li, B., Jin, X., Shi, Y., Li, Q., & Wei, X. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.114078 · Cited by 14
A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method
Chen, Y., Peng, H., Huang, L., Zhang, J., & Jiang, W. (2023) · IEEE Access · doi:10.1109/access.2023.3332475 · Cited by 11
Towards Total Online Unsupervised Anomaly Detection and Localization in Industrial VisionPreprint
Gao, H., Luo, H., Shen, F., & Zhang, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.15652 · Cited by 14
Wave-Mambaad: Wavelet-Driven State Space Model for Multi-Class Unsupervised Anomaly Detection
Qiao, Z., Shao, M., Chen, X. H., Lv, X., & Xu, K. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01940 · Cited by 16
Gu, Z., Zhu, B., Zhu, G., Chen, Y., Tang, M., & Wang, J. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3671805 · Cited by 14
FOCT: Few-shot Industrial Anomaly Detection with Foreground-aware Online Conditional Transport
Tian, L., Zhao, H., Lu, R., Wang, R., Wu, Y., Wang, L., He, X., & Liu, X. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680771 · Cited by 18
Towards Accurate Unified Anomaly Segmentation
Ma, W., Yao, Q., Zhang, X., Huang, Z., Jiang, Z., & Zhou, S. (2025) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00138 · Cited by 19
Liu, S., Chen, J., Liu, Z., Wang, J., & Wang, Z. J. (2024) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2024.110784 · Cited by 10
MiniMaxAD: A lightweight autoencoder for feature-rich anomaly detection
Wang, F., Liu, C., Shi, L., & Pang, H. (2025) · Computers in Industry · doi:10.1016/j.compind.2025.104315 · Cited by 11
Xia, X., Lv, W., He, X., Li, N., Liu, C., & Ding, N. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650356 · Cited by 9
A recover-then-discriminate framework for robust anomaly detection
Xing, P., Zhang, D., Tang, J., & Li, Z. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4291-4 · Cited by 10
An unsupervised deep global–local views model for anomaly detection in attributed networks
Lei, T., Ou, M., Gong, C., Li, J., & Yang, K. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112185 · Cited by 8
Self-citationSparse and semi-attention guided faults diagnosis approach for distributed online services
Zhang, L., & Shi, Y. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110911 · Cited by 8
WARM: A wavelet adaptive restoration module for surface anomaly detection
Qiao, Z., Lin, M., Lin, J., & Ding, D. (2024) · Measurement · doi:10.1016/j.measurement.2024.114689 · Cited by 10
Metadata
- Authors
- You, Z., Cui, L., Shen, Y., Yang, K., Lu, X., Zheng, Y., & Le, X.
- ORCID
- Lu, Xin
- Venue
- Advances in Neural Information Processing Systems 35
- Published
- 2022
- Pages
- 4571-4584
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133227337
- Cited by
- 303
- References
- 0
- Citations by year
- 2026: 115 · 2025: 76 · 2024: 87 · 2023: 25
- FWCI
- 25.97
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- neural information processing systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62176152)
- National Key Research and Development Program of China (2021YFB1716000)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- multi-class anomaly detection, unified model, anomaly detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.