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 301–377 of 377
Relation Prototype Re-Scoring for CLIP-Based Logical Anomaly Detection and Localization
Park, H. (2026) · Electronics · doi:10.3390/electronics15184293
Liu, C., Qi, P., Gao, R., & Tao, D. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.116309
Wang, Q., Lan, H., Zhou, T., Ma, N., Yang, H., & Yan, J. (2026) · Biomimetics · doi:10.3390/biomimetics11090679
Pang, J., Zhu, H., Li, H., & Zhai, Y. (2026) · International Conference on Electronic Information, Computer and Aerospace Remote Sensing (EICARS) · doi:10.1109/eicars71536.2026.11694559
Hierarchical Region-Guided Multi-Task Network for Energy Label Quality Inspection
Feng, Y., Yu, J. F., Zhang, Y., Hu, S., Feng, X., Yu, J., & Jing, Z. (2026) · Electronics · doi:10.3390/electronics15194374
Fast Dynamic Prototypes for Unsupervised Anomaly Detection and Localization
Li, M., Li, H., Wu, L. Y., Liu, C., & Zhao, X. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37225-3_21
Lin, J. C., Chen, P.-W., & Chen, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.15396
A Unified Dual Attention-Guided Reverse Distillation Framework for Anomaly Detection
Zhu, C., Xu, M., Feng, G., Zhang, M., & Niu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5597-4_32
Jha, R. R., Teja, A. S. S., Wadawadagi, V., & Tallamraju, R. B. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651095 · Cited by 1
Data-Augmented Denoising Diffusion Process for Few-Shot Anomaly DetectionPreprint
Coscia, P., Genovese, A., & Plataniotis, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5038206
MSSF: A Multi-scale Siamese Flow Architecture for Multi-texture Class Anomaly Detection
Chen, Y., Hu, Z., Huang, L., & Zhang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78447-7_3
Orthogonal Latent Compression for Streaming Anomaly Detection in Industrial Vision
Gao, H., Luo, H., Shen, F., & Zhang, Z. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78189-6_7
Novel Real-Time Anomaly Detection Approach for Data Analysis
Wang, H., Zhang, S., Zhang, L., Wang, Y., & Li, M. (2024) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici62993.2024.10810779
IRAD: Input-Reference Joint Driven Reconstruction for Unified Anomaly Detection
Chen, Z., Yao, X., Luo, Y., Liu, Z., Zhang, B., & Zhang, C. (2024) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip63160.2024.10849884
Wei, R., Fu, Y., & Liu, T. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889392
MSD: Mask-Guided and Semantic-Guided Diffusion-Based Framework for Stone Surface Defect Detection
Chen, L., Zheng, J., Xu, F., Lou, J. J., & Zeng, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-5809-1_22
Winchester, M., Husson, P., & Qu, X. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-94150-4_41
Chen, T., Jin, J., & Li, D. (2025) · International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM) · doi:10.1109/icmtim65484.2025.11040289
Wang, M., Hang, J., & Chen, D. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9961-2_21
Image-level Synthesis and Perturbation for Self-supervised Anomaly Detection
Kosugi, R., & Ando, S. (2025) · International Conference on Machine Learning and Human-Computer Interaction (MLHMI) · doi:10.1109/mlhmi66056.2025.00010
Feature Reconstruction via Reverse Distillation for Multi-class Anomaly Detection
Wang, J., Xu, H., Cai, Z., & Tu, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9921-6_26
Learning Visual Augmentations from Linguistic Knowledge Prior for Anomaly Detection
Jiang, X., Liu, X., Ding, Z., Sun, X., & Hu, Z. (2025) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc65474.2025.11091270
No-MambAAD: Revitalizing Conv-Only Networks for Unsupervised Anomaly Detection
Fahim, M. A. N. I., & Boutellier, J. J. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00383 · Cited by 1
Unsupervised Brain Tumor Segmentation via Bi-Level Optimization Guided by Radiological Reports
Zhang, P., Pang, H., Zhang, X., Gao, X., Liu, C., Hong, X., Jiang, R., Liu, Y., & Ye, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05472-2_3
Enhancing Small-Sample Defect Detection in Machinery Images via Multimodal Feature Perturbation
Bai, B., Zhang, M., & Zhang, X. (2025) · International Conference on Modeling, Natural Language Processing and Machine Learning (CMNM) · doi:10.1145/3757110.3757202
He, P., Wang, M., Yuan, X., & Li, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4091-4_18
Ada-CAD: Adaptive Distillation and Dynamic Neighbor Masked Attention for Continual Anomaly Detection
Yu, M., & Wang, F. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_16 · Cited by 1
A framework for unsupervised anomaly detection in real-world cable inspection
Lu, T., & Shao, P. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-025-05087-3
HLGFA: High-Low Resolution Guided Feature Alignment for Unsupervised Anomaly DetectionPreprint
Zhou, H., Gao, Y., Du, Y., & Zheng, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.09524
Ngoc, K. V., & Gia, H. D. (2026) · European Journal of Computer Science and Information Technology · doi:10.37745/ejcsit.2013/vol14n18596
Ngoc, K. V., & Gia, H. D. (2026) · European Journal of Biology and Medical Science Research · doi:10.37745/ejbmsr.2013/vol14n16475
Yingcheng, Z., Ning, Z., Xiaogang, S., Hei, X., & Zhenghao, S. (2026) · Journal of Image and Graphics · doi:10.11834/jig.250599
Shape–texture aware multi-source domain adaptation for industrial anomaly detection
Xie, Y., Li, L., Wang, Z., Zhou, Y., Peng, T., & Hu, X. (2026) · The Visual Computer · doi:10.1007/s00371-026-04377-2
Kim, M.-G., Kareem, A. B., Son, H.-M., & Hur, J.-W. (2026) · The Journal of Korean Institute of Information Technology · doi:10.14801/jkiit.2026.24.3.33
Yao, X., Qian, Z., Shi, C., Song, J., & Zhang, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.10971
Multi-Source Expert Scoring for zero-shot visual anomaly classification and segmentation
Gao, H., Guo, B., Li, Z., Zhong, X., Zhong, Y., & Dian, S. (2026) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2026.104794
De-FuSE—Disentangled Frequency and Semantic Embeddings for Unified Vision Anomaly Detection
Ishtiaq, M., & Won, J. (2026) · IEEE Access · doi:10.1109/access.2026.3689927
Wang, S., Han, Y., Qin, Y., Li, Y., Guo, Z., Yan, F., Su, L., Huang, H., Gu, T., & Zheng, P. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7084-3_22
Lv, X., Chen, H., & Wang, Z. G. (2026) · Solar Energy · doi:10.1016/j.solener.2026.114674
Multi-Scale Fuzzy Rough Sets Based Anomaly Detection With Multiple Autoencoders
Tan, X., Gao, C., Zhou, J., & Ding, W. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3688029
A diffusion-based framework with transformer blocks for anomaly detection
Wang, Z., Tan, X., & Tan, J. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115477 · Cited by 1
Fan, T., Chen, J., & Liu, X. (2026) · Scientific Reports · doi:10.1038/s41598-026-52590-9
Structure-aware anomaly detection via semantic prototype reconstruction in hyperbolic space
Feng, Y., Liu, J., & Gai, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-57393-6
A plug-and-play intra-class variance suppression framework for industrial anomaly detection
Song, Z., Ju, Y., Buayai, P., Jia, G., & Mao, X. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115404
FG-DiTAD: A Feature Guided Diffusion Transformer for Anomaly Detection
Du, M., Zhao, J., Zhang, L., Qin, Z., Xie, L., & Hu, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116462
Li, C., Yu, G., & Ye, W. (2026) · IEEE Access · doi:10.1109/access.2026.3707880
Qiao, S., & Liu, C. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-01084-9
Statistical Non-linear Reconstruction Loss for Image Anomaly Detection
Tri, N. M., Duy, H. K., & Ngu, H. C. V. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.306
RadarFusion: Real-Time Unsupervised Radar Target Detection with Single-step Diffusion Model
Shi, L., Liang, X., Chen, W., Zeng, Z., Feng, Y., Liu, Y., Meng, F., Chen, B., & Liu, H. (2026) · Digital Signal Processing · doi:10.1016/j.dsp.2026.106600
Isolating to Harness: Cross-Division Distillation for Fully Unsupervised Anomaly Detection
Liu, X., Wang, J., Leng, B., & Zhang, S. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3719070
Industrial anomaly detection via RGB-event fusion with multimodal large language models
Shi, R., Wei, J., Hou, X., Shi, H., Li, Y., Li, Y., & Guo, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-69071-8
DriftAD: Visually-Guided Text Drift for Few-Shot Industrial Anomaly Detection
Liu, W., Liu, T., Zhang, D., Wu, K., & Kong, A. W. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835539
Huang, Z., Zhang, E., Zhang, Z., He, Z., Liu, Y., & Chen, Y. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116368
VGCAD: Visual Geometry‐Guided Circulant Attention Distillation for Industrial Anomaly Detection
Ye, W., Peng, Z., Zeng, K., & Li, Z. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70938
Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection
Yang, M., Ding, L., Guo, Y., & Wang, F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37235-2_38
ReMem: A Dynamic Memory Evolution Detector for Zero-Shot Anomaly Detection
Yi, L., Chen, Z., Wu, G., Ding, J., Wang, X., & Ning, Z. (2026) · doi:10.1109/cvprf71909.2026.00739
Liu, J., Wang, P., Huang, J., Zhou, X., & Yu, L. (2026) · doi:10.1109/cvprf71909.2026.00582
MegAD: An Expert in Meta-Learning Guided Few-Shot Anomaly Detection
Li, X., Jing, J., Wu, T., Gao, T. S., & Sheng, Z. (2026) · doi:10.1109/cvprf71909.2026.00252
DGD: Density Gradient-Guided Diffusion for Long-Tailed Clustering
Ye, X., Deng, Y., & Zhou, K. (2026) · doi:10.1109/cvprf71909.2026.00735
Zhang, P., & Ren, W. (2026) · Sensors · doi:10.3390/s26206372
Wu, X., Wei, X., Zhu, Y., Duan, S., Zhang, X., Qian, Q., Song, J., & Dai, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135293
Multi-view patch inference with frozen DINOv3 for industrial anomaly detection
Wang, C., Zhang, W., Qi, B., Huang, X., & He, N. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02685-0
FasterAD: Faster and more precise multi-class unsupervised anomaly detection and localization
Tan, P., Chen, Z., & Wong, W. K. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115101
iCAS: An in-context anomaly segmentation framework for industrial visual inspection
Deng, H., Gao, B.-B., Jiang, X., Liu, Y., Wang, C., & Li, X. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.115085
Locality-aware transformer for multi-class industrial image anomaly detection
Wu, Y., Datago, A. M., & Tao, H. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02712-0
Uncertainty-Guided Dual-View Distillation for Industrial Anomaly Detection
Wei, C., Xi, X., Cao, G., & Nie, M. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729835
CDAD: A Multi-Scale Feature Fusion Model for Cross-Domain Anomaly Detection
Zhang, H., Wang, H., Jianyong, Z., & Wang, H. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729580
Wavelet Frequency-Decoupling and Flow-Based Mapping Framework for Anomaly Detection
Zhang, R., Fu, Z., & Tong, G. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11747-4
Decoupled dual-prior modulation for universal cross-domain anomaly detection
Zhao, C., Gu, J., Li, X., Hao, W., & Xie, H. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117267
Yu, Q., Li, H., & Wu, B. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105374
OAL-FOD: Object-Aware Learning for Open-Set Foreign Object Debris DetectionPreprint
Jiang, G., Cao, J., Zhang, J., Bai, Z., & Su, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7669365
Category-Conditioned Missing Masks for Inpainting-Based Image Anomaly Detection
Minami, Y., Nakanishi, K., & Tokunaga, T. (2026) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.2026nhp0009
Minding Anomaly Patterns via Uncertainty-Guided Heterogeneous Knowledge Distillation with Denoising
Li, Y., Yang, S., Wang, Y., Wang, B., Qi, J., & Shen, Q. (2026) · Big Data Mining and Analytics · doi:10.26599/bdma.2026.9020006
Normal‐Mode‐Aware Augmented Kernel One‐Class SVM for Heterogeneous Normality Modeling
Yu, W., Wu, J., & Hu, J. (2026) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.70453
Unified Traffic Sign Anomaly Detection via Template Guidance
Bischoff, N., & Tomforde, S. (2026) · International Conference on Machine Learning and Applications · doi:10.1109/icmla69890.2026.00084
AggCLIP: Aggregating CLIP for Zero-Shot Multimodal Anomaly Detection
Li, Z., Wang, H., Shen, F., & Zhang, Z. (2026) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3767308.3835551
Transformer-based multicategory unsupervised anomaly detection for fabric surfaces
Zeng, H., Zhou, S., Hu, W., Jiang, X., & Pan, F. (2026) · Textile Research Journal · doi:10.1177/00405175261502595
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.