FAPM: Fast Adaptive Patch Memory for Real-Time Industrial Anomaly Detection
Open accessAbstract
Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some methods do not meet the speed requirements of real-time inference, which is crucial for real-world applications. To address this issue, we propose a new method called Fast Adaptive Patch Memory (FAPM) for real-time industrial anomaly detection. FAPM utilizes patch-wise and layer-wise memory banks that store the embedding features of images at the patch and layer level, respectively, which eliminates unnecessary repetitive computations. We also propose patch-wise adaptive coreset sampling for faster and more accurate detection. FAPM performs well in both accuracy and speed compared to other state-of-the-art methods.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · see citing works
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244 · see citing works
MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
Bergmann, P., Fauser, M., Sattlegger, D., & Steger, C. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00982 · Cited by 2,203 · see citing works
Towards Total Recall in Industrial Anomaly Detection
Roth, K., Pemula, L., Zepeda, J., Scholkopf, B., Brox, T., & Gehler, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01392 · Cited by 1,810 · cited 18× · see citing works
“Layer-wise memory Many existing embedding features matching based methods include PatchCore [5] and Padim [4] concatenate mid-level features, which avoids being overly generic or too heavily biased towards ImageNet [17] classification [5].”
BackgroundMethodInfluentialAnomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction
Sakurada, M., & Yairi, T. (2014) · Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis · doi:10.1145/2689746.2689747 · Cited by 1,438 · see citing works
PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization
Defard, T., Setkov, A., Loesch, A., & Audigier, R. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-68799-1_35 · Cited by 1,415 · see citing works
Active Learning for Convolutional Neural Networks: A Core-Set Approach
Sener, O., & Savarese, S. (2017) · arXiv · doi:10.48550/arxiv.1708.00489 · Cited by 922 · see citing works
Gudovskiy, D., Ishizaka, S., & Kozuka, K. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv51458.2022.00188 · Cited by 669 · see citing works
Patch SVDD: Patch-Level SVDD for Anomaly Detection and Segmentation
Yi, J., & Yoon, S. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-69544-6_23 · Cited by 551 · see citing works
Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows
Rudolph, M., Wandt, B., & Rosenhahn, B. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00195 · Cited by 489 · see citing works
Sub-Image Anomaly Detection with Deep Pyramid Correspondences
Cohen, N., & Hoshen, Y. (2020) · arXiv · doi:10.48550/arxiv.2005.02357 · Cited by 372 · see citing works
Towards Visually Explaining Variational Autoencoders
Liu, W., Li, R., Zheng, M., Karanam, S., Wu, Z., Bhanu, B., Radke, R. J., & Camps, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00867 · Cited by 294 · see citing works
Geometric Approximation via Coresets
Agarwal, P. K., Har-Peled, S., & Varadarajan, K. (2005) · doi:10.1017/9781009701259.002 · Cited by 259 · see citing works
Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
Tao, X., Gong, X., Zhang, X., Yan, S., & Adak, C. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3196436 · Cited by 228 · see citing works
Inpainting transformer for anomaly detection
Pirnay, J., & Chai, K. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-06430-2_33 · Cited by 227 · see citing works
Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
Hou, J., Zhang, Y., Zhong, Q., Xie, D., Pu, S., & Zhou, H. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00867 · Cited by 202 · see citing works
Tang, T., Kuo, W.-H., Lan, J.-H., Ding, C., Hsu, H., & Young, H. (2020) · Sensors · doi:10.3390/s20123336 · Cited by 149 · see citing works
Tan, D. S., Chen, Y.-C., Chen, T. P.-C., & Chen, W.-C. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00032 · Cited by 83 · see citing works
Small-GAN: Speeding Up GAN Training Using Core-sets
Sinha, S., Zhang, H., Goyal, A., Bengio, Y., Larochelle, H., & Odena, A. (2019) · arXiv · doi:10.48550/arxiv.1910.13540 · Cited by 56 · see citing works
Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly DetectionPreprint
Wang, G., Han, S., Ding, E., & Huang, D. (2021) · arXiv (Cornell University) · Cited by 53 · see citing works
Two-Stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Park, C., Lee, M., Cho, S., Kim, D., & Lee, S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094881 · Cited by 5 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Deep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463 · see citing works
“FAPM [70] - ResNet The paper puts different position features of the image into different memory banks to speed up retrieval.”
InfluentialYang, Q., & Guo, R. (2024) · Sensors · doi:10.3390/s24082440 · Cited by 35 · see citing works
“Gaussian smoothing serves as a post-processing technique for image anomaly detection, generating a final score map by distributing each pixel’s score in a Gaussian distribution, a technique applied in various studies [34–36].”
MethodZUMA: Training-Free Zero-Shot Unified Multimodal Anomaly Detection
Ma, Y., Liu, M., Jiang, S., Zhou, J., Bian, Y., Wang, X., & Wang, Y. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3658856 · Cited by 4 · see citing works
- Authors
- Kim, D., Park, C., Cho, S., & Lee, S.
- Affiliations
- Yonsei University (KR)
- Venue
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2023-06-04
- Pages
- 1-5
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W4372341889
- Semantic Scholar
- af796ef97822338f5d96b2b5022ced4eef84d11a
- Cited by
- 56
- References
- 23
- Citations by year
- 2026: 8 · 2025: 18 · 2024: 24 · 2023: 6
- FWCI
- 9.90
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Acoustics Speech and Signal Processing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Yonsei University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- industrial anomaly detection, real-time inference, feature embedding, computational efficiency, image 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.
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
