{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:49:59Z","timestamp":1777567799044,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031801358","type":"print"},{"value":"9783031801365","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-80136-5_4","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T09:38:22Z","timestamp":1733045902000},"page":"48-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["P2A: Transforming Proposals to\u00a0Anomaly Masks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4073-4170","authenticated-orcid":false,"given":"Huachao","family":"Zhu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3038-6006","authenticated-orcid":false,"given":"Zhichao","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6689-9947","authenticated-orcid":false,"given":"Zelong","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7253-3151","authenticated-orcid":false,"given":"Yongchao","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Blum, H., Sarlin, P.E., Nieto, J., Siegwart, R., Cadena, C.: The Fishyscapes benchmark: measuring blind spots in semantic segmentation. Int. J. Comput. Vis. 129, 3119\u20133135 (2021)","DOI":"10.1007\/s11263-021-01511-6"},{"key":"4_CR2","unstructured":"Chan, R., et al.: Segmentmeifyoucan: a benchmark for anomaly segmentation. In: Proceedings of NeurIPS Datasets and Benchmarks (2021)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Chan, R., Rottmann, M., Gottschalk, H.: Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. In: Proceedings of ICLR, pp. 5128\u20135137 (2021)","DOI":"10.1109\/ICCV48922.2021.00508"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of ECCV, pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of CVPR, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of CVPR, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Proceedings of CVPR, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Di\u00a0Biase, G., Blum, H., Siegwart, R., Cadena, C.: Pixel-wise anomaly detection in complex driving scenes. In: Proceedings of CVPR, pp. 16918\u201316927 (2021)","DOI":"10.1109\/CVPR46437.2021.01664"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of CVPR, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Galesso, S., Argus, M., Brox, T.: Far away in the deep space: dense nearest-neighbor-based out-of-distribution detection. In: Proceedings of ICCV, pp. 4477\u20134487 (2023)","DOI":"10.1109\/ICCVW60793.2023.00482"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Galesso, S., Bravo, M.A., Naouar, M., Brox, T.: Probing contextual diversity for dense out-of-distribution detection. In: Proceedings of ECCV, pp. 492\u2013509 (2022)","DOI":"10.1007\/978-3-031-25072-9_34"},{"key":"4_CR13","unstructured":"Gao, Z., Yan, S., He, X.: ATTA: anomaly-aware test-time adaptation for out-of-distribution detection in segmentation. In: Proceedings of NeurIPS (2024)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Proceedings of ECCV, pp. 540\u2013557 (2022)","DOI":"10.1007\/978-3-031-20059-5_31"},{"issue":"4","key":"4_CR15","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.3390\/s24041248","volume":"24","author":"M Grci\u0107","year":"2024","unstructured":"Grci\u0107, M., Bevandi\u0107, P., Kalafati\u0107, Z., \u0160egvi\u0107, S.: Dense out-of-distribution detection by robust learning on synthetic negative data. Sensors 24(4), 1248 (2024)","journal-title":"Sensors"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Grci\u0107, M., Bevandi\u0107, P., \u0160egvi\u0107, S.: Densehybrid: hybrid anomaly detection for dense open-set recognition. In: Proceedings of ECCV, pp. 500\u2013517 (2022)","DOI":"10.1007\/978-3-031-19806-9_29"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"4_CR18","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016)"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Jung, S., Lee, J., Gwak, D., Choi, S., Choo, J.: Standardized max logits: a simple yet effective approach for identifying unexpected road obstacles in urban-scene segmentation. In: Proceedings of ICCV, pp. 15425\u201315434 (2021)","DOI":"10.1109\/ICCV48922.2021.01514"},{"key":"4_CR20","unstructured":"Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian SegNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of ICCV, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4_CR22","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: Proceedings of ICLR (2022)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of CVPR, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Proceedings of ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Lis, K., Nakka, K., Fua, P., Salzmann, M.: Detecting the unexpected via image resynthesis. In: Proceedings of ICCV, pp. 2152\u20132161 (2019)","DOI":"10.1109\/ICCV.2019.00224"},{"key":"4_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Nayal, N., Yavuz, M., Henriques, J.F., G\u00fcney, F.: RbA: segmenting unknown regions rejected by all. In: Proceedings of ICCV, pp. 711\u2013722 (2023)","DOI":"10.1109\/ICCV51070.2023.00072"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Pinggera, P., Ramos, S., Gehrig, S., Franke, U., Rother, C., Mester, R.: Lost and found: detecting small road hazards for self-driving vehicles. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1099\u20131106 (2016)","DOI":"10.1109\/IROS.2016.7759186"},{"key":"4_CR29","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of ICML, pp. 8748\u20138763 (2021)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Rai, S.N., Cermelli, F., Fontanel, D., Masone, C., Caputo, B.: Unmasking anomalies in road-scene segmentation. In: Proceedings of ICCV, pp. 4037\u20134046 (2023)","DOI":"10.1109\/ICCV51070.2023.00373"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"4_CR32","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: Proceedings of ICLR (2020)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Tian, Y., Liu, Y., Pang, G., Liu, F., Chen, Y., Carneiro, G.: Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes. In: Proceedings of ECCV, pp. 246\u2013263 (2022)","DOI":"10.1007\/978-3-031-19842-7_15"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: DiffuMask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. arXiv preprint arXiv:2303.11681 (2023)","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhang, Y., Liu, F., Shen, W., Yuille, A.L.: Synthesize then compare: detecting failures and anomalies for semantic segmentation. In: Proceedings of ECCV, pp. 145\u2013161 (2020)","DOI":"10.1007\/978-3-030-58452-8_9"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, W., Li, X., Liu, Z., Ong, Y.S., Loy, C.C.: MosaicFusion: diffusion models as data augmenters for large vocabulary instance segmentation. arXiv preprint arXiv:2309.13042 (2023)","DOI":"10.1007\/s11263-024-02223-3"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: Proceedings of CVPR, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of CVPR, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Proceedings of ECCV, pp. 736\u2013753. Springer (2022)","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of CVPR, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of CVPR, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80136-5_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T10:02:28Z","timestamp":1733047348000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80136-5_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031801358","9783031801365"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80136-5_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}