pith. sign in

arxiv: 2606.28688 · v1 · pith:MXRGB6FMnew · submitted 2026-06-27 · 💻 cs.CV

LogiCo: A Unified Framework for Logical and Structural Anomaly Detection

Ximiao Zhang , Min Xu , Xiuzhuang Zhou This is my paper

Pith reviewed 2026-06-30 10:02 UTC · model grok-4.3

classification 💻 cs.CV
keywords anomaly detectionlogical anomaliesstructural anomaliesfeature reconstructioncomponent-level featuresMVTec-LOCOcomputer visionindustrial inspection
0
0 comments X

The pith

LogiCo unifies logical and structural anomaly detection by reconstructing features at component and patch levels from pre-trained images.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces LogiCo as a single model that addresses both logical anomalies, which violate rules about how components should relate, and structural anomalies, which are local appearance defects. Prior approaches either model global semantics for logical cases but lose fine-grained detection or focus only on structural issues. LogiCo maps pre-trained features into a discrete space of components and reconstructs them collaboratively at component and patch scales to encode constraints between parts implicitly. A segmentation-map discriminator is added to handle count-based logical errors. The result is leading performance across four standard benchmarks covering both anomaly types.

Core claim

By mapping pre-trained image features into a discrete component-level feature space and performing collaborative feature reconstruction at both component and patch levels, LogiCo captures inter-component logical constraints without explicit global semantic modeling, supplemented by a segmentation-map discriminator for count-related anomalies, achieving state-of-the-art results on MVTec-LOCO, MVTec-AD, VisA, and Real-IAD.

What carries the argument

Component-level feature reconstruction that discretizes pre-trained features into components and reconstructs them jointly at component and patch scales to enforce logical relations between components.

If this is right

  • The same model can flag both rule violations between parts and local defects without switching architectures.
  • Patch-level reconstruction preserves the ability to detect small structural changes that global semantic models overlook.
  • The added segmentation discriminator directly addresses quantitative logical anomalies such as incorrect object counts.
  • Unified training on mixed anomaly types yields top scores on dedicated logical benchmarks like MVTec-LOCO and structural ones like MVTec-AD.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Discrete component spaces may serve as a lightweight substitute for explicit scene graphs in other constraint-satisfaction vision tasks.
  • The dual reconstruction scales could transfer to detecting logical inconsistencies in video by treating frames as successive component sets.
  • Industrial inspection pipelines might consolidate separate logical and structural detectors into one component-reconstruction stage.

Load-bearing premise

Mapping pre-trained image features into a discrete component-level feature space and performing collaborative reconstruction at component and patch levels suffices to capture inter-component logical constraints without explicit global semantic modeling.

What would settle it

A controlled test where the method is applied to a new dataset containing logical constraints that cannot be expressed through component co-occurrence or reconstruction error, resulting in performance no better than random or below specialized logical detectors while structural performance remains intact.

Figures

Figures reproduced from arXiv: 2606.28688 by Min Xu, Ximiao Zhang, Xiuzhuang Zhou.

Figure 1
Figure 1. Figure 1: (a): Examples of structural and logical anomalies. (b): Comparison of the overall pipelines between LogiCo and global semantic modeling-based methods. (c): Compari￾son of LogiCo with other methods on anomaly detection and localization performance. anomalies, as illustrated in [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the proposed LogiCo pipeline, which consists of a Component￾level Reconstruction Network (CRN), a Structural Reconstruction Network (SRN), and a Segmentation Map Discriminator (SMD). The CRN and SRN learn global logical constraints and local structural consistency to detect logical and structural anomalies, respectively, whereas the SMD learns quantity rules to identify count-related anomalies.… view at source ↗
Figure 3
Figure 3. Figure 3: Examples of segmentation maps generated by various anomaly synthesis meth￾ods. by assigning the corresponding component prototype to each spatial location: \label {eq:equ3} X_\mathtt {c}(i,j) = \mathrm {f}_{G(i,j)}. (3) It offers two key advantages: (1) The component-level feature map preserves the image’s spatial layout and essential information for logical anomaly detection while filtering out irrelevant… view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparison of LogiCo and other methods on logical anomaly de￾tection. anomaly detection and localization performance, respectively, noting that sPRO is specifically designed for logical anomalies. Following previous work [4, 14, 18], metrics for logical and structural anomalies are computed separately, and their average is reported as the overall metric. Baselines. For structural anomaly detect… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative comparison of LogiCo and other methods on structural anomaly detection. Peach Breakfast Box Orange Cereals Banana Chips Almonds Lunch Box Black Background Pushpins Pushpins Storage Box Black Background Screw Bag Metal Bolt Metal Hex Nut Zip-lock Bag Black Background Metal Flat Washer Splicing Connectors Blue Cable Yellow Cable Connector Grid Red Cable Banana Juice Orange Juice Yellow Sticker Gl… view at source ↗
Figure 6
Figure 6. Figure 6: Examples of component segmentation on the MVTec-LOCO dataset. and AnomalyMoE [15], detect logical defects more effectively but lag signifi￾cantly behind on benchmarks characterized by subtle structural anomalies, par￾ticularly on the challenging VisA [55] and Real-IAD [40] datasets. In contrast, LogiCo demonstrates superior performance across all benchmarks. Specifically, it achieves an impressive 96.3% I-… view at source ↗
read the original abstract

Current anomaly detection methods primarily focus on structural anomalies, while paying insufficient attention to anomalies that violate logical constraints. Conversely, top-performing logical anomaly detection approaches address this by modeling global semantic consistency, but perform poorly on subtle structural anomalies due to inadequate detection granularity. In this paper, we propose LogiCo, a unified framework for Logical and structural anomaly detection via Component-level feature reconstruction. Unlike existing methods that rely on explicit global semantic modeling, LogiCo employs a novel component-level feature reconstruction technique to capture inter-component logical constraints. Specifically, LogiCo maps pre-trained image features into a discrete component-level feature space and performs collaborative feature reconstruction at both component and patch levels, enabling it to effectively detect both logical and structural anomalies. Furthermore, to address the specific challenge of count-related logical anomalies, we integrate a segmentation-map discriminator that extends the model's capability to identify quantitative inconsistencies. LogiCo achieves state-of-the-art performance on both logical and structural anomaly detection across four benchmarks, including MVTec-LOCO, MVTec-AD, VisA, and Real-IAD, demonstrating its superiority and practical feasibility. The code is available at https://github.com/cnulab/LogiCo.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes LogiCo, a unified framework for logical and structural anomaly detection via component-level feature reconstruction. It maps pre-trained image features into a discrete component-level feature space, performs collaborative feature reconstruction at both component and patch levels, and integrates a segmentation-map discriminator for count-related logical anomalies. The framework claims to achieve state-of-the-art performance on MVTec-LOCO, MVTec-AD, VisA, and Real-IAD benchmarks.

Significance. If the results hold, the work could be significant for providing a single model that addresses both logical constraints (via component-level reconstruction) and structural anomalies (via patch-level reconstruction) without explicit global semantic modeling, which is a noted limitation of prior approaches.

major comments (1)
  1. [Abstract] Abstract: the claim of state-of-the-art performance on four benchmarks is asserted without any quantitative results, tables, error bars, or methodological details, making it impossible to verify support for the central performance claim.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and for highlighting the need for stronger support of the central performance claim in the abstract. We address this point below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim of state-of-the-art performance on four benchmarks is asserted without any quantitative results, tables, error bars, or methodological details, making it impossible to verify support for the central performance claim.

    Authors: We agree that the abstract would be strengthened by including key quantitative results to immediately substantiate the SOTA claim. While abstracts are concise by nature and detailed tables/error bars belong in the main text (where they are provided in Tables 1-4 with standard deviations), we will revise the abstract to incorporate specific metrics, such as the average AUROC improvements on MVTec-LOCO, MVTec-AD, VisA, and Real-IAD. This revision will make the performance claim verifiable at a glance without altering the abstract's length constraints. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The provided abstract and description contain no equations, derivations, fitted parameters presented as predictions, or self-citations. The method is described at a high level as mapping features and performing reconstruction, with no load-bearing step shown that reduces to its own inputs by construction. The central claim is empirical SOTA performance on benchmarks, which is independent of any internal derivation chain. Full manuscript details are referenced but absent from the query, precluding identification of any circular steps.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract does not specify any free parameters, axioms, or invented entities; the review is limited to the abstract provided.

pith-pipeline@v0.9.1-grok · 5740 in / 1057 out tokens · 38250 ms · 2026-06-30T10:02:18.565993+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

55 extracted references · 4 canonical work pages · 1 internal anchor

  1. [1]

    In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision

    Bae, J., Lee, J.H., Kim, S.: Pni: industrial anomaly detection using position and neighborhood information. In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision. pp. 6373–6383 (2023)

    2023

  2. [2]

    In: Proceedings of the IEEE/CVF winter conference on applications of computer vision

    Batzner, K., Heckler, L., König, R.: Efficientad: Accurate visual anomaly detection at millisecond-level latencies. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision. pp. 128–138 (2024)

    2024

  3. [3]

    International Journal of Computer Vision129(4), 1038–1059 (2021)

    Bergmann, P., Batzner, K., Fauser, M., Sattlegger, D., Steger, C.: The mvtec anomaly detection dataset: a comprehensive real-world dataset for unsupervised anomaly detection. International Journal of Computer Vision129(4), 1038–1059 (2021)

    2021

  4. [4]

    International Journal of Computer Vision130(4), 947–969 (2022)

    Bergmann,P.,Batzner,K.,Fauser,M.,Sattlegger,D.,Steger,C.:Beyonddentsand scratches: Logical constraints in unsupervised anomaly detection and localization. International Journal of Computer Vision130(4), 947–969 (2022)

    2022

  5. [5]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Mvtec ad–a comprehen- sive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9592–9600 (2019)

    2019

  6. [6]

    In: Pro- ceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In: Pro- ceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 4183–4192 (2020)

    2020

  7. [7]

    In: International Conference on Medical Im- age Computing and Computer-Assisted Intervention

    Cai, Y., Chen, H., Yang, X., Zhou, Y., Cheng, K.T.: Dual-distribution discrepancy for anomaly detection in chest x-rays. In: International Conference on Medical Im- age Computing and Computer-Assisted Intervention. pp. 584–593. Springer (2022)

    2022

  8. [8]

    In: 2025 IEEE/CVF Winter Con- ference on Applications of Computer Vision (WACV)

    Damm, S., Laszkiewicz, M., Lederer, J., Fischer, A.: Anomalydino: Boosting patch- based few-shot anomaly detection with dinov2. In: 2025 IEEE/CVF Winter Con- ference on Applications of Computer Vision (WACV). pp. 1319–1329. IEEE (2025)

    2025

  9. [9]

    In: The Twelfth International Conference on Learning Representations (2024)

    Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need regis- ters. In: The Twelfth International Conference on Learning Representations (2024)

    2024

  10. [10]

    In: International conference on pattern recognition

    Defard,T.,Setkov,A.,Loesch,A.,Audigier,R.:Padim:apatchdistributionmodel- ing framework for anomaly detection and localization. In: International conference on pattern recognition. pp. 475–489. Springer (2021)

    2021

  11. [11]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Deng, H., Li, X.: Anomaly detection via reverse distillation from one-class embed- ding. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9737–9746 (2022) 16 X. Zhang et al

    2022

  12. [12]

    International Journal of Computer Vision131(10), 2553–2581 (2023)

    Diers, J., Pigorsch, C.: A survey of methods for automated quality control based on images. International Journal of Computer Vision131(10), 2553–2581 (2023)

    2023

  13. [13]

    In: European conference on computer vision

    Fučka, M., Zavrtanik, V., Skočaj, D.: Transfusion–a transparency-based diffusion model for anomaly detection. In: European conference on computer vision. pp. 91–108. Springer (2024)

    2024

  14. [14]

    In: Proceedings of the IEEE/CVF International Conference on Computer Vision

    Fučka, M., Zavrtanik, V., Skočaj, D.: Salad–semantics-aware logical anomaly de- tection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. pp. 21843–21852 (2025)

    2025

  15. [15]

    In: Proceedings of the AAAI Conference on Artificial Intelligence

    Gu, Z., Zhu, B., Zhu, G., Chen, Y., Ge, W., Tang, M., Wang, J.: Anomalymoe: Towards a language-free generalist model for unified visual anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 40, pp. 4348– 4356 (2026)

    2026

  16. [16]

    In: Proceedings of the IEEE/CVF winter conference on applications of computer vision

    Gudovskiy,D.,Ishizaka,S.,Kozuka,K.:Cflow-ad:Real-timeunsupervisedanomaly detection with localization via conditional normalizing flows. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision. pp. 98–107 (2022)

    2022

  17. [17]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Guo, J., Lu, S., Zhang, W., Chen, F., Li, H., Liao, H.: Dinomaly: The less is more philosophy in multi-class unsupervised anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 20405–20415 (2025)

    2025

  18. [18]

    In: 35th British Machine Vision Conference 2024, BMVC 2024, Glasgow, UK, November 25-28, 2024

    Hsieh, Y.H., Lai, S.H.: Csad: Unsupervised component segmentation for logical anomaly detection. In: 35th British Machine Vision Conference 2024, BMVC 2024, Glasgow, UK, November 25-28, 2024. BMVA (2024)

    2024

  19. [19]

    Hu, T., Zhang, J., Yi, R., Du, Y., Chen, X., Liu, L., Wang, Y., Wang, C.: Anomaly- diffusion:Few-shotanomalyimagegenerationwithdiffusionmodel.In:Proceedings of the AAAI conference on artificial intelligence. vol. 38, pp. 8526–8534 (2024)

    2024

  20. [20]

    The Visual Computer36(1), 85–96 (2020)

    Huang, Y., Qiu, C., Yuan, K.: Surface defect saliency of magnetic tile. The Visual Computer36(1), 85–96 (2020)

    2020

  21. [21]

    In: Proceedings of the AAAI conference on artificial intelligence

    Kim, S., An, S., Chikontwe, P., Kang, M., Adeli, E., Pohl, K.M., Park, S.H.: Few shot part segmentation reveals compositional logic for industrial anomaly detec- tion. In: Proceedings of the AAAI conference on artificial intelligence. vol. 38, pp. 8591–8599 (2024)

    2024

  22. [22]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y., et al.: Segment anything. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 4015–4026 (2023)

    2023

  23. [23]

    In: European Conference on Computer Vision

    Lee, J.C., Kim, T., Park, E., Woo, S.S., Ko, J.H.: Continuous memory represen- tation for anomaly detection. In: European Conference on Computer Vision. pp. 438–454. Springer (2024)

    2024

  24. [24]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Lei, J., Hu, X., Wang, Y., Liu, D.: Pyramidflow: High-resolution defect contrastive localization using pyramid normalizing flow. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 14143–14152 (2023)

    2023

  25. [25]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Li, C.L., Sohn, K., Yoon, J., Pfister, T.: Cutpaste: Self-supervised learning for anomaly detection and localization. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 9664–9674 (2021)

    2021

  26. [26]

    arXiv preprint arXiv:2503.14910 (2025)

    Liao, J., Xu, X., Su, Y., Tu, R.C., Liu, Y., Tao, D., Yang, X.: Robust distribution alignment for industrial anomaly detection under distribution shift. arXiv preprint arXiv:2503.14910 (2025)

    work page arXiv 2025

  27. [27]

    Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection.In:ProceedingsoftheIEEEinternationalconferenceoncomputervision. pp. 2980–2988 (2017) LogiCo: A Unified Framework for Logical and Structural Anomaly Detection 17

    2017

  28. [28]

    Machine Intelligence Research21(1), 104–135 (2024)

    Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., Jin, Y.: Deep industrial image anomaly detection: A survey. Machine Intelligence Research21(1), 104–135 (2024)

    2024

  29. [29]

    In: Proceedings of the Computer Vision and Pattern Recognition Con- ference

    Luo, W., Cao, Y., Yao, H., Zhang, X., Lou, J., Cheng, Y., Shen, W., Yu, W.: Exploring intrinsic normal prototypes within a single image for universal anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Con- ference. pp. 9974–9983 (2025)

    2025

  30. [30]

    Knowledge-Based Systems 314, 113176 (2025)

    Peng, Y., Lin, X., Ma, N., Du, J., Liu, C., Liu, C., Chen, Q.: Sam-lad: Segment any- thing model meets zero-shot logic anomaly detection. Knowledge-Based Systems 314, 113176 (2025)

    2025

  31. [31]

    IEEE Transactions on Circuits and Systems for Video Technology (2026)

    Peng, Y., Lin, X., Ma, N., Liu, C., Chen, Q.: Vllm-lad: Visual large language model for zero-shot logical anomaly detection. IEEE Transactions on Circuits and Systems for Video Technology (2026)

    2026

  32. [32]

    In: 2020 25th International Conference on Pattern Recognition (ICPR)

    Rippel, O., Mertens, P., Merhof, D.: Modeling the distribution of normal data in pre-trained deep features for anomaly detection. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 6726–6733. IEEE (2021)

    2020

  33. [33]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Roth, K., Pemula, L., Zepeda, J., Schölkopf, B., Brox, T., Gehler, P.: Towards total recall in industrial anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 14318–14328 (2022)

    2022

  34. [34]

    In: European Conference on Com- puter Vision

    Schlüter, H.M., Tan, J., Hou, B., Kainz, B.: Natural synthetic anomalies for self- supervised anomaly detection and localization. In: European Conference on Com- puter Vision. pp. 474–489. Springer (2022)

    2022

  35. [35]

    DINOv3

    Siméoni, O., Vo, H.V., Seitzer, M., Baldassarre, F., Oquab, M., Jose, C., Khali- dov, V., Szafraniec, M., Yi, S., Ramamonjisoa, M., et al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  36. [36]

    In: 2024 IEEE International Conference on Image Processing (ICIP)

    Sugawara, S., Imamura, R.: Puad: Frustratingly simple method for robust anomaly detection. In: 2024 IEEE International Conference on Image Processing (ICIP). pp. 842–848. IEEE (2024)

    2024

  37. [37]

    IEEE Transactions on Instru- mentation and Measurement71, 1–21 (2022)

    Tao, X., Gong, X., Zhang, X., Yan, S., Adak, C.: Deep learning for unsupervised anomaly localization in industrial images: A survey. IEEE Transactions on Instru- mentation and Measurement71, 1–21 (2022)

    2022

  38. [38]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Tien, T.D., Nguyen, A.T., Tran, N.H., Huy, T.D., Duong, S., Nguyen, C.D.T., Truong, S.Q.: Revisiting reverse distillation for anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 24511–24520 (2023)

    2023

  39. [39]

    In: 2025 IEEE International Conference on Robotics and Automation (ICRA)

    Tong, X., Chang, Y., Zhao, Q., Yu, J., Wang, B., Lin, J., Lin, Y., Mai, X., Wang, H., Tao, Z., et al.: Component-aware unsupervised logical anomaly generation for industrial anomaly detection. In: 2025 IEEE International Conference on Robotics and Automation (ICRA). pp. 16722–16729. IEEE (2025)

    2025

  40. [40]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang, C., Zhu, W., Gao, B.B., Gan, Z., Zhang, J., Gu, Z., Qian, S., Chen, M., Ma, L.: Real-iad: A real-world multi-view dataset for benchmarking versatile industrial anomaly detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 22883–22892 (2024)

    2024

  41. [41]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Wei, S., Jiang, J., Xu, X.: Uninet: A contrastive learning-guided unified framework with feature selection for anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 9994–10003 (2025)

    2025

  42. [42]

    In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition

    Wyatt, J., Leach, A., Schmon, S.M., Willcocks, C.G.: Anoddpm: Anomaly detec- tion with denoising diffusion probabilistic models using simplex noise. In: Proceed- ings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 650–656 (2022) 18 X. Zhang et al

    2022

  43. [43]

    Xiang, T., Zhang, Y., Lu, Y., Yuille, A.L., Zhang, C., Cai, W., Zhou, Z.: Squid: Deepfeaturein-paintingforunsupervisedanomalydetection.In:Proceedingsofthe IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 23890– 23901 (2023)

    2023

  44. [44]

    IEEE Trans- actions on Circuits and Systems for Video Technology34(5), 3589–3605 (2023)

    Yao, H., Yu, W., Luo, W., Qiang, Z., Luo, D., Zhang, X.: Learning global-local cor- respondence with semantic bottleneck for logical anomaly detection. IEEE Trans- actions on Circuits and Systems for Video Technology34(5), 3589–3605 (2023)

    2023

  45. [45]

    Advances in Neural Information Processing Systems 35, 4571–4584 (2022)

    You, Z., Cui, L., Shen, Y., Yang, K., Lu, X., Zheng, Y., Le, X.: A unified model for multi-class anomaly detection. Advances in Neural Information Processing Systems 35, 4571–4584 (2022)

    2022

  46. [46]

    arXiv preprint arXiv:2111.07677 (2021)

    Yu, J., Zheng, Y., Wang, X., Li, W., Wu, Y., Zhao, R., Wu, L.: Fastflow: Unsuper- vised anomaly detection and localization via 2d normalizing flows. arXiv preprint arXiv:2111.07677 (2021)

    work page arXiv 2021

  47. [47]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Zavrtanik, V., Kristan, M., Skočaj, D.: Draem-a discriminatively trained re- construction embedding for surface anomaly detection. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 8330–8339 (2021)

    2021

  48. [48]

    In: European conference on computer vision

    Zavrtanik, V., Kristan, M., Skočaj, D.: Dsr–a dual subspace re-projection network for surface anomaly detection. In: European conference on computer vision. pp. 539–554. Springer (2022)

    2022

  49. [49]

    Computer Vision and Image Understanding253, 104308 (2025)

    Zhang, J., Chen, X., Wang, Y., Wang, C., Liu, Y., Li, X., Yang, M.H., Tao, D.: Exploring plain vit features for multi-class unsupervised visual anomaly detection. Computer Vision and Image Understanding253, 104308 (2025)

    2025

  50. [50]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Zhang, J., Wang, G., Jin, Y., Huang, D.: Towards training-free anomaly detection with vision and language foundation models. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 15204–15213 (2025)

    2025

  51. [51]

    In: International Conference on Medical Image Computing and Computer-Assisted Intervention

    Zhang, X., Xu, M., Qiu, D., Yan, R., Lang, N., Zhou, X.: Mediclip: Adapting clip for few-shot medical image anomaly detection. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 458–468. Springer (2024)

    2024

  52. [52]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Zhang, X., Xu, M., Zhou, X.: Realnet: A feature selection network with realis- tic synthetic anomaly for anomaly detection. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 16699–16708 (2024)

    2024

  53. [53]

    arXiv preprint arXiv:2508.12931 (2025)

    Zhang, X., Xu, M., Zhou, X.: Towards high-resolution industrial image anomaly detection. arXiv preprint arXiv:2508.12931 (2025)

    work page arXiv 2025

  54. [54]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhao, Y.: Logical: Towards logical anomaly synthesis for unsupervised anomaly localization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 4022–4031 (2024)

    2024

  55. [55]

    Breakfast Box

    Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self- supervised pre-training for anomaly detection and segmentation. In: European conference on computer vision. pp. 392–408. Springer (2022) LogiCo: A Unified Framework for Logical and Structural Anomaly Detection Supplementary Material Ximiao Zhang1, Min Xu2, and Xiuzhuang Zhou1...

    2022