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
Items 201–300 of 377
Scale-aware modulation network for unsupervised medical anomaly detection
Cao, H., Sun, S., & Yan, H. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133672 · Cited by 2
RDNA: reconstruction discriminant networks with adversarial training for anomaly detection
Liu, X., Li, S., Cheng, Y., & Luo, X. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12084-1 · Cited by 1
DecoupleMAD: Boosting sensitivity in multimodal anomaly detection via representation decoupling
Zhao, Y., Li, B., Zhang, X., Zhang, L., & Lu, H. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114025 · Cited by 1
Dual-stream semantic-texture network for rolling bearing defect detection
Yin, Z., Yu, Y., Han, G., Qin, L., Zhang, F., & Han, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134089 · Cited by 1
Lee, J., 양진철, Kim, G., Kim, U., Roh, J., Song, Y., Lee, H. J., Lim, H., & Kang, S. (2026) · Journal of Information Display · doi:10.1007/s44469-026-00014-9 · Cited by 1
SimpleZ3D: A simple framework for zero-shot 3D industrial anomaly detection
Gao, H., Zhao, W., Zhong, Y., Wang, M., & Zhang, J. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114237 · Cited by 1
MATCH: Flow Matching for Multi-view Anomaly Detection
Kruse, M., Schween, M., & Rosenhahn, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37152-2_16 · Cited by 1
tan, Z., Hu, H., Xu, J., Li, M. J., & Sun, X. G. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae8c77 · Cited by 1
Zhang, H. M. (2026) · IEEE Access · doi:10.1109/access.2026.3714579 · Cited by 1
An Information-Aware Reconstruction Model for Multicategory 3-D Anomaly Detection
Liang, H., Gao, C., Niu, Z., Zhang, J., Wang, J., & Shen, L. (2026) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2026.3717889 · Cited by 1
Explainable Multitype Anomaly Detection Using a Lightweight Fully Convolutional Architecture
George, A., Mihaylova, L. S., & Anderson, S. R. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/4983395 · Cited by 1
Anomaly Agent: Unified Anomaly Retrieval and Synthesis Before Manufacturing
Li, X., Wang, X., Yao, S., Sun, M., & Wu, Y. (2026) · doi:10.1109/cvprf71909.2026.00419 · Cited by 1
Zhu, W., Liang, J., Cheng, L., Pan, Y., Chen, Z., Yan, Q., Cheng, Y., Zhang, J., Chi, M., & Peng, B. (2026) · doi:10.1109/cvprf71909.2026.00202 · Cited by 1
Zhan, D., Wang, H., Wei, C., Gao, S., 王宏睿, Song, Y., & Liu, Z. (2026) · International Journal of Rail Transportation · doi:10.1080/23248378.2026.2740544 · Cited by 1
Factorized Industrial Anomaly Detection and Localization
Zhu, Y., Dai, L., Dong, X., & Li, P. (2023) · IEEE Access · doi:10.1109/access.2023.3265715 · Cited by 1
Unsupervised PCB Anomaly Segmentation with Foundational Models
Ho, C.-H., Seo, S.-B., Kim, N., Wu, P.-Y., Bae, Y., & Vasconcelos, N. M. (2024) · Electronic Imaging · doi:10.2352/ei.2024.36.6.iriacv-277 · Cited by 1
Attend, Distill, Detect: Attention-Aware Entropy Distillation for Anomaly Detection
Jena, S., Saini, V., Shaw, U., Jain, P., Raihal, A. S., Banerjee, A., Joshi, S., Ganesh, A., & Bhavsar, A. V. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78169-8_17 · Cited by 1
FDC-Net: foreground dynamic capture with deep feature enhancement for video anomaly detection
Shi, R., He, Q., Wang, H., & Zhang, C. (2025) · Multimedia Systems · doi:10.1007/s00530-025-01692-x · Cited by 1
DN-DR: Discriminative Network with Dual Reconstruction for Image Anomaly Detection
Li, W., & Zhang, C. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888690 · Cited by 1
Anoonly: Semi-Supervised Anomaly Detection with the Only Loss on AnomaliesPreprint
Zhou, Y., Yang, P., Qu, Y., Xu, X., Sun, Z., & Cichocki, A. S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4640554 · Cited by 1
Beyond Human-prompting: Adaptive Prompt Tuning with Semantic Alignment for Anomaly DetectionPreprint
Chen, P.-W., Lin, J. C.-W., Chen, W.-H., Ji, J., Chen, Z.-C., Yeh, F.-H., & Chen, C.-C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.16157 · Cited by 1
MOPDA: Mixed-Trajectory On-Policy Distillation for Language-Guided Industrial Anomaly DetectionPreprint
Chen, S., Jin, J., Su, N., Xu, H., Cheng, Z., Yang, W., Ma, F., & Wang, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.18850 · Cited by 1
Surface Anomaly Detection on Shock Absorber Connecting Rods Using an Enhanced PatchCore Algorithm
Yueqi, Z. H. O. U., Jialin, C. U. I., Bin, L. I. A. N., Hao, L. U. O., ZHENG, Y., & Zhe-Ming, L. U. (2025) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2025edl8047
Self-citationZhu, H., Liu, Z., Sun, Z., Dong, W., Xiao, X., Zhang, Z., & Xu, Y. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3668690 · Cited by 3
ClipMPCAD: Few-Shot Anomaly Detection with LLM-Guided Prompts and Multi-Attention Fusion
Han, Y., Wang, S., Xue, Y., Guo, Z., Jin, K., Li, J., Wang, L., Li, Y., & Zheng, P. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401924
UAD-X: A Universal Anomaly Detection Framework for X-Ray Inspection of Electronic Components
Bai, H., Wang, J., Li, G., Li, X., Zhang, X., & Yang, X. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3670570
AirNet: Self-Supervised Anomaly Detection for Aircraft Instrument Screens
Yin, Z., Yuan, L., Liu, S., Xu, F., & Wang, W. (2025) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc68654.2025.11437648
Hierarchical Interaction Distillation for Industrial Anomaly Detection from Cross-Type Perspective
Liao, X., Huang, G., Chen, Y., & Chen, X. (2025) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc68654.2025.11438131
Park, J., Lee, J.-H., Kim, N., Park, C., Hwang, J., Ra, S., & Gwak, J. (2026) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2026.24.3.45
Mayaki, M. Z. A. (2024) · theses.fr (ABES) · doi:10.70675/e8e2614az79ffz4901z9c79ze9f9889ba9c4
Semi-supervised deep learning for robust anomaly detection in smart manufacturing systems
Le, T. (2024) · theses.fr (ABES) · doi:10.70675/19d23228zf030z4df7za3abz596d36577818
Zhang, T., Pang, W., & Lu, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3684998
Self-citationWang, D., Cheng, Q., Zhang, C., Dai, J., Zhen, C., & Ge, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465131
Revisiting Reconstruction-Based Anomaly Detection for Whole-Slide Image
Xiao, B., Wangulu, C., van der Kwast, T., Yousef, G. M., & Zabihollahy, F. (2026) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2026.3687008
CNC-Former: Multiclass Unsupervised Surface Defect Detection for CNC Precision Parts
Yin, Z., Yuan, L., Zhang, F., Shi, X., & Qin, L. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3687332
A Multi-Class Anomaly Detection Method Based on Reverse Distillation and Mixed-Attention
Yun, J., Liu, M., & Li, Y. (2025) · International Conference on Industrial Automation, Robotics and Control Engineering (IARCE) · doi:10.1109/iarce68366.2025.11485697
Enhancing Reverse Distillation with Core Exemplar Learning for Unified Multi-Class Anomaly Detection
Lim, H., Kim, M. U., Lee, H. J., Kang, S., Chon, K.-W., & Lee, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00732
PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection
Huang, P., Li, J.-L., Huang, P.-H., Chang, M., & Chen, W.-C. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00536 · Cited by 2
Towards Active Real-to-Twin Inspection: A New Paradigm for Zero-Shot Anomaly Detection
Liu, J., Cao, Y., Chen, Y., Li, C., Du, Y., & Zhang, H. (2026) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber71431.2026.11695467
Weatherly, C., & Lin, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37393-9_5
Khanam, M., Yaseen, M. U., Imran, M., Raza, B., & Faheem, M. (2026) · The Journal of Engineering · doi:10.1049/tje2.70194
Zhu, J., Fan, Y., Han, G., Shi, X., Deng, F., & Chen, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11591-w · Cited by 1
A Method for Anomaly Detection of Train Components Based on Feature Reconstruction
Yang, Z., Xiaorong, G., Luo, L., & Jianqiang, G. (2025) · IEEE Far East NDT New Technology & Application Forum (FENDT) · doi:10.1109/fendt66689.2025.11547363
SaF-AD: Saliency-Adaptive and Feature-Consistent Diffusion for Industrial Anomaly Detection
Liu, Y., Zhang, Y., Luo, Z., Xu, K., Xu, Y., & Yao, L. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810806
SAND: Semantic-Aware Anomaly Detection with Region-Consistent Memory for Noisy Training
Xu, K., Zhang, Y., Liu, Y., Luo, Z., He, Y., & Yao, L. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810738
Li, J., Lu, B., & Zhang, W. (2026) · The Visual Computer · doi:10.1007/s00371-026-04580-1
Beyond image generation: visual data analysis with diffusion models—a comprehensive survey
Olechno, B., & Mańdziuk, J. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11615-5
Industrial anomaly generation via mask-guided dual reverse inpainting for visual inspection
Hu, X., Liu, Z., & Yang, H. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134313
Boundary-Aware Structural-Semantic Pseudo Anomaly Learning for Industrial Anomaly DetectionPreprint
Guo, C., Jiang, H., Ying, N., & Shen, L. (2026) · Research Square · doi:10.21203/rs.3.rs-9925157/v1
Liu, Y., Liu, D., Wang, Q., Yu, Q., Li, J., & Guo, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6981432
Decontaminating Anomaly Detection: A Geometric Adversarial Approach With Stochastic Bottlenecks
Zhang, Q., Xu, S., Li, Z., Zeng, K., Liu, G., & Wu, R. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3705036
DeCoFlow: Structural Decomposition of Normalizing Flows for Continual Anomaly Detection
Im, H., Lee, J., Cha, S., & Kang, P. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37092-1_5
Condition-guided unified diffusion for unsupervised multi-class anomaly detection
Gu, H., Lv, Y., & Liu, Z. (2026) · Signal Processing Image Communication · doi:10.1016/j.image.2026.117643
ProtoXModal: Few-Shot Anomaly Detection via Gated Prototype-Level Cross-Modal Knowledge Transfer
Li, Y. X. (2026) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis70043.2026.11572331
BinaryAD: Efficient image anomaly detection via binarized representations
Chen, J. K., Zhang, W., Wang, P., Guo, B., Liang, H., Shen, L., Wang, J., & Lu, Z. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114280
LogiCo: A Unified Framework for Logical and Structural Anomaly Detection
Zhang, X., Xu, M., & Zhou, X. J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37550-6_14 · Cited by 1
Zhou, Y., Zhao, J. Z., Zeng, D., Luo, X., Liang, H., & Wu, Z. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114367
LiteFusion: Adaptive Lightweight Fusion in Unsupervised Anomaly Localization
Zhao, Y., Yang, K., Chen, L., Lin, Q., Ye, P., & Lan, J. (2026) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc69287.2026.11579977
Self-citationA Unified Framework for Multi-class Unsupervised Anomaly Detection with State Space Model
Ma, X., Xu, Y., Xu, X., Li, Y., & Li, D. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582467
A dispersion-regularized normal image restoration network for anomaly detection and localization
Pang, J., & Li, C. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116591
Region-Prompt-Guided Anomaly Detection With Entropy-Based Consistency Modeling
Shi, Y., Xu, R., & Qi, Z. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3709516
Fine-Grained Enhancement Convolutional Diffusion Transformer for Unsupervised Anomaly Detection
Ma, Z., Fang, X., Huang, Y., Wen, J., Zhou, G., & Xu, Y. D. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3709502 · Cited by 1
Jeong, J.-H., Choi, Y.-R., Choi, Y., Cho, D.-Y., & Kim, M.-S. (2026) · Sensors · doi:10.3390/s26144372
Yin, B., & Wen, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3432-5_45
Zhang, H., Pan, D., & Jiang, Z. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3712912
MPFA-Net: Multi-perspective Feature Aggregation and Saliency Reweighting for Image Anomaly Detection
Li, L., Hao, T., Li, X., Liu, H., Zhai, L., Li, Z., Wu, Y., Cui, L., & Tong, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3507-0_14
Self-citation3D brain image anomaly detection using anomaly-guided large vision-language models
Yang, K., Zhang, Z., Zhou, Y., Yang, J., Guo, J., & Wen, S. (2026) · The Visual Computer · doi:10.1007/s00371-026-04622-8
Self-citationShi, Y., Liu, C., & Yu, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3378-6_38
Relation-Aware Representation Learning for Label-Free Unified Multi-Class Anomaly Detection
Kim, H., Heo, J., Kim, J., Lee, J., & Seo, W. (2026) · Asia Conference on Computer Vision, Image Processing and Pattern Recognition (CVIPPR) · doi:10.1109/cvippr69607.2026.11604494
TCEAD: Multi-class Unsupervised Anomaly Detection Model with Trainable Canonical Embedding
Wu, Y. T., Wang, J., Yao, W., Chen, Y., & Liang, E. (2026) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai70103.2026.11605700
Shen, H., Yang, H., He, L., Zhu, Q., & Wang, K. (2026) · Measurement · doi:10.1016/j.measurement.2026.122642
AG-DPF: adaptive gating-based dual-prototype fusion framework for metal anomaly detection
Chen, C. Y. J., Li, Y., Chen, M., Zhang, H., Dong, Z. L. W., & Wei, S. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02932-1
Semantic-Preserving Dense Localization via DINO-Guided Refinement of CLIP Anomaly Maps
Park, H. (2026) · Electronics · doi:10.3390/electronics15153309
Qian, H., Han, Z., Hong, W., Yang, H., Wang, H., Li, J., & Liu, Z. (2026) · Sensors · doi:10.3390/s26154783
A comprehensive survey on industrial image anomaly detection
Beddawi, C., Haddad, Y., Achkar, C. E., & Makhoul, A. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21809-2
CKM: Continual Anomaly Detection Based on Compact Knowledge Memory
Liu, Y., Li, Q., Sun, W., & Wang, W. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3698601
Yang, L., 梁发强, Xie, S., & Nie, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31933-3_36
DCRS: Attention-Guided Dual-Channel Reasoning Segmentation for Industrial Anomaly Detection
Jin, R., zeng, J., Li, H., Bai, Z., Lin, H., & Yang, L. (2026) · Information Fusion · doi:10.2139/ssrn.7227212
Unsupervised Transformer Framework for Real-World Furniture Surface Defect Detection
Wu, X., Wang, L., & Chen, X. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-92-0607-0_25
ProtoFocus: Industrial Anomaly Detection with Prototype distillation and Latent InhibitionPreprint
Zha, C., Yuan, J., Liu, R., & Jiang, N. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7238277
魏泽夫, Liu, Z., Chen, G., Zhou, X., Wang, F., & Li, P. (2026) · IET Intelligent Transport Systems · doi:10.1049/itr2.70291
PADFormer: Pose-Agnostic Anomaly Detection from Sparse View Images
Wang, R., Qian, Y., Yu, F., Lu, Y., Wang, D., Zhang, H., & Huang, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37602-2_11
SCFE-AD: Structural Consistency Feature Enhancement for Industrial Anomaly Detection
Zhai, Y., Liu, Z., Yang, X., Chen, X., & Cui, Z. (2026) · IEEE International Conference on Computer Vision and Deep Learning (DLCV) · doi:10.1109/dlcv69906.2026.11635114
Fang, C.-H., Jou, J.-D., Chiu, Y.-H., & Hsu, G.-S. J. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630309
Robust Unified Anomaly Detection Via Spatially Gated Semantic Priors
Shi, H. (2026) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl70130.2026.11637990
Research on the Application of Visual Anomaly Detection Technology in Semiconductor Wafer Inspection
Chen, B., & Su, H. (2026) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr69988.2026.11642647
DFP-AD: A Dynamic Frequency Prototype Framework for Unsupervised Anomaly Detection
Zhang, Q., Shao, M., Chen, X., Lv, X., Meng, L., & Liu, C. (2026) · Information Fusion · doi:10.1016/j.inffus.2026.104728
Moon, A.-S., Jung, S.-H., Zulkifley, M. A., & Lee, J. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01762-4
MedUAD: Task-aware unsupervised continual learning for multimodal medical anomaly detection
Zhao, L., Lin, Q., Qi, X., Pu, B., Zheng, F., Tang, Z., Zhu, C., & Pun, C. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114806
CopilotAD: A Simple Method Based on ViT for Multi-class Logical Anomaly Detection
Cai, C., San, H., & Kono, M. (2026) · International Conference on Communications, Circuits and Systems · doi:10.1109/icccas70754.2026.11672508
GeoFusionNet: A geometry-aware fusion network for bearing surface defect detection
Wang, S., Lv, Z., & Li, Y. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105178
Deng, Y., Zhan, L., Nianjiong, Y., Li, J., & Hao, G. (2026) · IEEE Access · doi:10.1109/access.2026.3731018
Vision-guided multi-image prompt learning for zero and few-shot pipeline anomaly detection
Wu, C., Wang, Y., Qiao, B., & Zhang, H. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02652-9
DFDC: Dual-Frequency Decoupling and Correlation for time series anomaly detection
Lin, X., Dong, J., Li, Z., Wen, J., & Wu, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114855
Kim, S., Kim, T., Kim, D., Han, J. Y., Yun, H., Kim, J., Huh, K., Heo, M.-S., Lee, S.-S., Yang, S., et al. (2026) · International Dental Journal · doi:10.1016/j.identj.2026.111107
Prototype-Guided Diffusion Model for Multi-Class Unsupervised Anomaly Detection
Yu, J., Oh, H., Sun, Z., Harit, A., Yoo, N., & Yang, J. (2026) · IEEE Access · doi:10.1109/access.2026.3732635
TAMCA: Time-Aware Multi-Scale Convolutional Attention for Multi-Class Industrial Anomaly Detection
Li, X., Guan, Y., Jiang, J., Ye, M., Yan, H., & Zhang, C. (2026) · Eng—Advances in Engineering · doi:10.3390/eng7090480
Li, Y., Wu, H., Liu, Z., Chen, X., & Xi, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135143
翁, 长. (2026) · Journal of Sensor Technology and Application · doi:10.12677/jsta.2026.145083
Lv, N., Zhang, S., Guo, C., Yue, H., & Mei, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7493772
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.