{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:33:53Z","timestamp":1774967633758,"version":"3.50.1"},"reference-count":28,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation\n              https:\/\/ror.org\/01g0hqq23","doi-asserted-by":"publisher","award":["IITP-2026-RS-2022-00156360"],"award-info":[{"award-number":["IITP-2026-RS-2022-00156360"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Trade Industry & Energy\n              https:\/\/ror.org\/008nkqk13","award":["RS-2025-02317274"],"award-info":[{"award-number":["RS-2025-02317274"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As deep learning-based Anomaly Detection (AD) transitions from theoretical research to industrial application, the focus is shifting towards operational efficiency and economic viability on edge devices. While recent studies have achieved remarkable detection accuracy on standard benchmarks, they often rely on heavy memory banks or complex backbones, which pose challenges for deployment in resource-constrained manufacturing environments. Furthermore, real-world inspection lines often present distinct challenges\u2014such as environmental noise and strict latency requirements\u2014that are not fully addressed by accuracy-centric metrics. To bridge the gap between high-performance research models and practical edge deployment, we introduce WEDGE-Net. Our approach is designed to balance structural precision with extreme memory efficiency. We decouple anomaly detection into two specialized streams: (1) a Frequency Stream (DWT) that physically filters out environmental noise to isolate structural defects, and (2) a Context Stream where a Semantic Module explicitly guides feature extraction to enforce object consistency. By synthesizing these two modalities, WEDGE-Net effectively suppresses high-frequency noise while enhancing structural-feature compactness. To validate operational stability, we conducted a robustness analysis of the \u2018Tile\u2019 category, which poses a challenging task for distinguishing defects from high-frequency textures. In this stress test, WEDGE-Net demonstrated superior resistance to environmental noise compared to conventional methods. Experimental results on the MVTec AD dataset demonstrate that WEDGE-Net achieves a mean image-level AUROC of 97.82% and an inference speed of 686.5 FPS (measured on an RTX 4090 GPU) under an extreme 1% memory-compression setting. Notably, our method demonstrates superior efficiency, achieving a 2.1\u00d7 inference speedup over the widely adopted comparative model (PatchCore-10%) while maintaining competitive detection accuracy (e.g., 100% AUROC on Transistor). We hope this work serves as a practical reference for implementing real-time industrial inspection on resource-constrained edge devices.<\/jats:p>","DOI":"10.3390\/s26072154","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:23:17Z","timestamp":1774963397000},"page":"2154","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WEDGE-Net: Wavelet-Driven Memory-Efficient Anomaly Detection for Industrial Edge Computing"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3919-6703","authenticated-orcid":false,"given":"Joon-Min","family":"Park","sequence":"first","affiliation":[{"name":"School of Software, Soongsil University, Seoul 06978, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-6920","authenticated-orcid":false,"given":"Gye-Young","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Software, Soongsil University, Seoul 06978, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Czimmermann, T., Ciuti, G., Milazzo, M., Chiurazzi, M., Roccella, S., Oddo, C.M., and Dario, P. (2020). Visual-Based Defect Detection and Classification Approaches for Industrial Applications\u2014A Survey. Sensors, 20.","DOI":"10.3390\/s20051459"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1007\/s10845-019-01476-x","article-title":"Segmentation-Based Deep-Learning Approach for Surface-Defect Detection","volume":"31","author":"Tabernik","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_3","first-page":"5018021","article-title":"Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey","volume":"71","author":"Tao","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_4","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, B., Brox, T., and Gehler, P. (2022, January 18\u201324). PatchCore: Being Data-Efficient for Anomaly Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"8114","DOI":"10.1109\/TWC.2025.3564356","article-title":"Task-Driven Priority-Aware Computation Offloading Using Deep Reinforcement Learning","volume":"24","author":"Hao","year":"2025","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"16211","DOI":"10.1109\/TNNLS.2023.3292512","article-title":"A Dynamic Weights-Based Wavelet Attention Neural Network for Defect Detection","volume":"35","author":"Liu","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Bergmann, P., L\u00f6we, S., Fauser, M., Sattlegger, D., and Steger, C. (2018, January 27\u201329). Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders. Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), Funchal, Portugal.","DOI":"10.5220\/0007364503720380"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Schlegl, T., Seeb\u00f6ck, P., Waldstein, S.M., Schmidt-Erfurth, U., and Langs, G. (2017, January 25\u201330). Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery. Proceedings of the International Conference on Information Processing in Medical Imaging (IPMI), Boone, NC, USA.","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Akcay, S., Atapour-Abarghouei, A., and Breckon, T.P. (2018, January 2\u20136). GANomaly: Semi-supervised anomaly detection via adversarial training. Proceedings of the Asian Conference on Computer Vision (ACCV), Perth, Australia.","DOI":"10.1007\/978-3-030-20893-6_39"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zavrtanik, V., Kristan, M., and Sko\u010daj, D. (2021, January 11\u201317). DRAEM-A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wyatt, J., Leach, A., Schmon, S.M., and Willcocks, C.G. (2022, January 19\u201320). AnoDDPM: Anomaly Detection with Denoising Diffusion Probabilistic Models using Simplex Noise. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, New Orleans, LA, USA.","DOI":"10.1109\/CVPRW56347.2022.00080"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_13","unstructured":"Cohen, N., and Hoshen, Y. (2020). Sub-Image Anomaly Detection with Deep Pyramid Correspondences. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Defard, T., Setkov, A., Loesch, A., and Audigier, R. (2021, January 10\u201315). PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization. Proceedings of the International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1007\/978-3-030-68799-1_35"},{"key":"ref_15","unstructured":"Yu, J., Zheng, Y., Wang, X., Li, W., Wu, Y., Zhao, R., and Wu, L. (2021). FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gudovskiy, D., Ishizaka, S., and Kozuka, K. (2022, January 4\u20138). CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Deng, H., and Li, X. (2022, January 18\u201324). Anomaly Detection via Reverse Distillation from One-Class Embedding. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, Y., Xu, Y., and Wang, Z. (2023, January 18\u201322). SimpleNet: A Simple Network for Image Anomaly Detection and Localization. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Batzner, K., Heckler, L., and K\u00f6nig, R. (2024, January 4\u20138). EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00020"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, Q., Shen, L., Guo, S., and Lai, Z. (2020, January 13\u201319). Wavelet Integrated CNNs for Noise-Robust Image Classification. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00727"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"156966","DOI":"10.1109\/ACCESS.2019.2947606","article-title":"Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection","volume":"7","author":"Han","year":"2019","journal-title":"IEEE Access"},{"key":"ref_22","unstructured":"Zhang, X., Li, S., and Li, Z. (2021). Fourier transformation autoencoders for anomaly detection. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jiang, L., Dai, B., Wu, W., and Loy, C.C. (2021, January 11\u201317). Focal frequency loss for image reconstruction and synthesis. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.01366"},{"key":"ref_24","unstructured":"Mallat, S. (2009). A Wavelet Tour of Signal Processing: The Sparse Way, Academic Press. [3rd ed.]."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., and Steger, C. (2019, January 15\u201320). MVTec AD\u2013A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref_26","first-page":"2456","article-title":"Noise robustness of deep learning in industrial visual inspection","volume":"17","author":"Li","year":"2021","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_27","unstructured":"Olyunin, A., Kiselev, A., and Lomonosov, A. (2021). Challenges of Deep Learning Deployment in Real-World Industrial Environments: A Survey on Sensor Noise and Data Drift. Sensors, 21."},{"key":"ref_28","first-page":"52","article-title":"Machine Vision Intelligence for Product Defect Inspection Based on Deep Learning and Hough Transform","volume":"59","author":"Wang","year":"2021","journal-title":"J. Manuf. Syst."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2154\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:31:19Z","timestamp":1774963879000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/7\/2154"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":28,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["s26072154"],"URL":"https:\/\/doi.org\/10.3390\/s26072154","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]}}}