{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T12:50:52Z","timestamp":1755694252156,"version":"3.41.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031928048","type":"print"},{"value":"9783031928055","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-92805-5_11","type":"book-chapter","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T12:58:57Z","timestamp":1747918737000},"page":"166-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SQUAD: Scalar Quantized Representation Learning for\u00a0Unsupervised Anomaly Detection and\u00a0Localization"],"prefix":"10.1007","author":[{"given":"Shih-Chih","family":"Lin","sequence":"first","affiliation":[]},{"given":"Shang-Hong","family":"Lai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Tschannen, M., Mentzer, F., Timofte, R., Gool, L.V.: Generative adversarial networks for extreme learned image compression. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 221\u2013231 (2019)","DOI":"10.1109\/ICCV.2019.00031"},{"key":"11_CR2","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: MVTEC ad\u2013a comprehensive real-world dataset for unsupervised anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9592\u20139600 (2019)","DOI":"10.1109\/CVPR.2019.00982"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Uninformed students: student-teacher anomaly detection with discriminative latent embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4183\u20134192 (2020)","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Bergmann, P., L\u00f6we, S., Fauser, M., Sattlegger, D., Steger, C.: Improving unsupervised defect segmentation by applying structural similarity to autoencoders. arXiv preprint arXiv:1807.02011 (2018)","DOI":"10.5220\/0007364503720380"},{"key":"11_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2021.103459","volume":"129","author":"J Bo\u017ei\u010d","year":"2021","unstructured":"Bo\u017ei\u010d, J., Tabernik, D., Sko\u010daj, D.: Mixed supervision for surface-defect detection: from weakly to fully supervised learning. Comput. Ind. 129, 103459 (2021)","journal-title":"Comput. Ind."},{"key":"11_CR7","unstructured":"Cao, Y., et al.: A survey on visual anomaly detection: Challenge, approach, and prospect. arXiv preprint arXiv:2401.16402 (2024)"},{"key":"11_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-030-68799-1_35","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"T Defard","year":"2021","unstructured":"Defard, T., Setkov, A., Loesch, A., Audigier, R.: PaDiM: a patch distribution modeling framework for anomaly detection and localization. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12664, pp. 475\u2013489. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68799-1_35"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Deng, H., Li, X.: Anomaly detection via reverse distillation from one-class embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9737\u20139746, June 2022","DOI":"10.1109\/CVPR52688.2022.00951"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, X., Li, H., Liu, J., Hu, Q., Xiao, J.: Fastrecon: few-shot industrial anomaly detection via fast feature reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17481\u201317490 (2023)","DOI":"10.1109\/ICCV51070.2023.01603"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Groenendijk, R., Karaoglu, S., Gevers, T., Mensink, T.: Multi-loss weighting with coefficient of variations. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1469\u20131478 (2021)","DOI":"10.1109\/WACV48630.2021.00151"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Gudovskiy, D., Ishizaka, S., Kozuka, K.: CFLOW-AD: real-time unsupervised anomaly detection with localization via conditional normalizing flows. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 98\u2013107 (2022)","DOI":"10.1109\/WACV51458.2022.00188"},{"key":"11_CR13","unstructured":"Huh, M., Cheung, B., Agrawal, P., Isola, P.: Straightening out the straight-through estimator: overcoming optimization challenges in vector quantized networks. In: International Conference on Machine Learning, pp. 14096\u201314113. PMLR (2023)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Jezek, S., Jonak, M., Burget, R., Dvorak, P., Skotak, M.: Deep learning-based defect detection of metal parts: evaluating current methods in complex conditions. In: 2021 13th International congress on ultra modern telecommunications and control systems and workshops (ICUMT), pp. 66\u201371. IEEE (2021)","DOI":"10.1109\/ICUMT54235.2021.9631567"},{"issue":"2","key":"11_CR15","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/TII.2022.3199228","volume":"19","author":"J Jiang","year":"2022","unstructured":"Jiang, J., et al.: Masked Swin transformer uNet for industrial anomaly detection. IEEE Trans. Industr. Inf. 19(2), 2200\u20132209 (2022)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"\u0141a\u0144cucki, A., et al.: Robust training of vector quantized bottleneck models. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207145"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"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\u20139674 (2021)","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Lin, J., Yan, Y.: A comprehensive augmentation framework for anomaly detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 8742\u20138749 (2024)","DOI":"10.1609\/aaai.v38i8.28720"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, Y., Xu, Y., Wang, Z.: Simplenet: A simple network for image anomaly detection and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20402\u201320411 (2023)","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"11_CR22","unstructured":"Mentzer, F., Minnen, D., Agustsson, E., Tschannen, M.: Finite scalar quantization: Vq-vae made simple. arXiv preprint arXiv:2309.15505 (2023)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Mishra, P., Verk, R., Fornasier, D., Piciarelli, C., Foresti, G.L.: VT-ADL: a vision transformer network for image anomaly detection and localization. In: 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), pp. 01\u201306. IEEE (2021)","DOI":"10.1109\/ISIE45552.2021.9576231"},{"issue":"3","key":"11_CR25","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1145\/325165.325247","volume":"19","author":"K Perlin","year":"1985","unstructured":"Perlin, K.: An image synthesizer. ACM SIGGRAPH Comput. Graph. 19(3), 287\u2013296 (1985)","journal-title":"ACM SIGGRAPH Comput. Graph."},{"key":"11_CR26","unstructured":"Razavi, A., Van\u00a0den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Ristea, N.C., et al.: Self-supervised predictive convolutional attentive block for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13576\u201313586 (2022)","DOI":"10.1109\/CVPR52688.2022.01321"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Roth, K., Pemula, L., Zepeda, J., Sch\u00f6lkopf, 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\u201314328 (2022)","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Schl\u00fcter, H.M., Tan, J., Hou, B., Kainz, B.: Natural synthetic anomalies for self-supervised anomaly detection and localization. In: vidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13691, pp. 474\u2013489. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_27","DOI":"10.1007\/978-3-031-19821-2_27"},{"key":"11_CR30","unstructured":"Takida, Y., et al.: SQ-VAE: Variational bayes on discrete representation with self-annealed stochastic quantization. arXiv preprint arXiv:2205.07547 (2022)"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Tien, T.D., et al.: Revisiting reverse distillation for anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24511\u201324520 (2023)","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"11_CR32","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"11_CR33","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/TASLP.2019.2950099","volume":"28","author":"X Wang","year":"2019","unstructured":"Wang, X., Takaki, S., Yamagishi, J., King, S., Tokuda, K.: A vector quantized variational autoencoder (VQ-VAE) autoregressive neural $$ f_0 $$ model for statistical parametric speech synthesis. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 157\u2013170 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"11_CR34","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I.S., Xie, S.: Convnext v2: Co-designing and scaling convnets with masked autoencoders. arXiv preprint arXiv:2301.00808 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"11_CR36","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGan. arXiv preprint arXiv:2110.04627 (2021)"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Zavrtanik, V., Kristan, M., Sko\u010daj, D.: Draem-a discriminatively trained reconstruction embedding for surface anomaly detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8330\u20138339 (2021)","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"11_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107706","volume":"112","author":"V Zavrtanik","year":"2021","unstructured":"Zavrtanik, V., Kristan, M., Sko\u010daj, D.: Reconstruction by inpainting for visual anomaly detection. Pattern Recogn. 112, 107706 (2021)","journal-title":"Pattern Recogn."},{"key":"11_CR39","doi-asserted-by":"publisher","unstructured":"Zavrtanik, V., Kristan, M., Sko\u010daj, D.: DSR - a dual subspace re-projection network for surface anomaly detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13691, pp. 539\u2013594. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_31","DOI":"10.1007\/978-3-031-19821-2_31"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wu, Z., Wang, Z., Chen, Z., Jiang, Y.G.: Prototypical residual networks for anomaly detection and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16281\u201316291 (2023)","DOI":"10.1109\/CVPR52729.2023.01562"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, N., Li, J., Dai, T., Jiang, Y., Xia, S.T.: Unsupervised surface anomaly detection with diffusion probabilistic model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6782\u20136791 (2023)","DOI":"10.1109\/ICCV51070.2023.00624"},{"key":"11_CR42","unstructured":"Zhu, Z., et al.: Designing a better asymmetric VQGan for stable diffusion. arXiv preprint arXiv:2306.04632 (2023)"},{"key":"11_CR43","doi-asserted-by":"publisher","unstructured":"Zou, Y., Jeong, J., Pemula, L., Zhang, D., Dabeer, O.: Spot-the-difference self-supervised pre-training for anomaly detection and segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision. ECCV 2022. LNCS, vol. 13690, pp. 392\u2013408. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_23","DOI":"10.1007\/978-3-031-20056-4_23"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92805-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T12:59:23Z","timestamp":1747918763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92805-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031928048","9783031928055"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92805-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}