{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T03:30:37Z","timestamp":1771558237902,"version":"3.50.1"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031916717","type":"print"},{"value":"9783031916724","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\/978-3-031-91672-4_6","type":"book-chapter","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:26:03Z","timestamp":1747754763000},"page":"80-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["SOOD-ImageNet: A\u00a0Large-Scale Dataset for\u00a0Semantic Out-of-Distribution Image Classification and\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2945-8758","authenticated-orcid":false,"given":"Alberto","family":"Bacchin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1180-9290","authenticated-orcid":false,"given":"Davide","family":"Allegro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-8719","authenticated-orcid":false,"given":"Stefano","family":"Ghidoni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5794-9979","authenticated-orcid":false,"given":"Emanuele","family":"Menegatti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Angarano, S., Martini, M., Navone, A., Chiaberge, M.: Domain generalization for crop segmentation with standardized ensemble knowledge distillation. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 5450\u20135459 (2024)","DOI":"10.1109\/CVPRW63382.2024.00554"},{"key":"6_CR2","unstructured":"Bashkirova, D., et al.: VISDA 2022 challenge: domain adaptation for industrial waste sorting. In: Proceedings of the NeurIPS 2022 Competitions Track, pp. 104\u2013118 (2022)"},{"key":"6_CR3","unstructured":"Beyer, L., et\u00a0al.: Paligemma: a versatile 3B VLM for transfer. arXiv preprint arXiv:2407.07726 (2024)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: IEEE Conference on Computing Vision Pattern Recognition, pp. 24185\u201324198 (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3606\u20133613 (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Conde, M.V., Turgutlu, K.: Clip-art: Contrastive pre-training for fine-grained art classification. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 3956\u20133960 (2021)","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"6_CR7","unstructured":"Corley, I.: Torchseg. https:\/\/github.com\/isaaccorley\/torchseg"},{"key":"6_CR8","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: IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"6_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., Van Gool, L., Williams, C., 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":"6_CR11","unstructured":"Filos, A., Tigkas, P., McAllister, R., Rhinehart, N., Levine, S., Gal, Y.: Can autonomous vehicles identify, recover from, and adapt to distribution shifts? In: International Conference on Machine Learning, pp. 3145\u20133153. PMLR (2020)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. In: International Conference on Computer Vision, pp. 8340\u20138349 (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"6_CR14","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: International Conference on Learning Representations (2019)"},{"key":"6_CR15","unstructured":"Hendrycks*, D., Mu*, N., Cubuk, E.D., Zoph, B., Gilmer, J., Lakshminarayanan, B.: Augmix: a simple method to improve robustness and uncertainty under data shift. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=S1gmrxHFvB"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15262\u201315271 (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"6_CR17","unstructured":"Horn, G.V., Cole, E., Beery, S., Wilber, K., Belongie, S., MacAodha, O.: Benchmarking representation learning for natural world image collections. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12879\u201312888 (2021)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Howard, A.G., et al.: Searching for mobilenetv3. In: International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Huang, R., Li, Y.: MOS: tTowards scaling out-of-distribution detection for large semantic space. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8710\u20138719 (2021)","DOI":"10.1109\/CVPR46437.2021.00860"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Khandelwal, A., Weihs, L., Mottaghi, R., Kembhavi, A.: Simple but effective: Clip embeddings for embodied AI. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14829\u201314838 (2022)","DOI":"10.1109\/CVPR52688.2022.01441"},{"key":"6_CR21","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Master\u2019s thesis, University of Toronto (2009)"},{"key":"6_CR22","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., et al.: The open images dataset v4: unified image classification, object detection, and visual relationship detection at scale. Int. J. Comput. Vis. 128, 1956\u20131981 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Lang, N., Sn\u00e6bjarnarson, V., Cole, E., Mac\u00a0Aodha, O., Igel, C., Belongie, S.: From coarse to fine-grained open-set recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17804\u201317814 (2024)","DOI":"10.1109\/CVPR52733.2024.01686"},{"key":"6_CR24","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_CR26","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer v2: scaling up capacity and resolution. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"6_CR29","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2017)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Mao, X., et al.: COCO-O: a benchmark for object detectors under natural distribution shifts. In: International Conference on Computer Vision, pp. 6316\u20136327 (2023)","DOI":"10.1109\/ICCV51070.2023.00583"},{"issue":"11","key":"6_CR32","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"6_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"6_CR34","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-Bert: Sentence embeddings using SIAMESE Bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"6_CR36","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik, L.: Imagenet-21k pretraining for the masses. In: Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (2021)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"7","key":"6_CR38","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","volume":"35","author":"WJ Scheirer","year":"2013","unstructured":"Scheirer, W.J., de Rezende Rocha, A., Sapkota, A., Boult, T.E.: Toward open set recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1757\u20131772 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR39","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, vol.\u00a097, pp. 6105\u20136114. PMLR (2019)"},{"key":"6_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106669","volume":"126","author":"H Thisanke","year":"2023","unstructured":"Thisanke, H., Deshan, C., Chamith, K., Seneviratne, S., Vidanaarachchi, R., Herath, D.: Semantic segmentation using vision transformers: a survey. Eng. Appl. Artif. Intell. 126, 106669 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"6_CR41","unstructured":"Trabucco, B., Doherty, K., Gurinas, M.A., Salakhutdinov, R.: Effective data augmentation with diffusion models. In: International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=ZWzUA9zeAg"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: MAXVIT: multi-axis vision transformer. In: European Conference on Computer Vision, pp. 459\u2013479. Springer (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: The INaturalist species classification and detection dataset. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"6_CR44","unstructured":"Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Open-set recognition: A good closed-set classifier is all you need. In: International Conference on Learning Representations (2022)"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Wang, H., Li, Z., Feng, L., Zhang, W.: Vim: Out-of-distribution with virtual-logit matching. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4921\u20134930 (2022)","DOI":"10.1109\/CVPR52688.2022.00487"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond pascal: a benchmark for 3D object detection in the wild. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"6_CR47","doi-asserted-by":"crossref","unstructured":"Xiao, B., et al.: Florence-2: advancing a unified representation for a variety of vision tasks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4818\u20134829 (2024)","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"6_CR48","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Xu, K., et al.: Precision weed detection in wheat fields for agriculture 4.0: a survey of enabling technologies, methods, and research challenges. Comput. Electron. Agric. 212, 108106 (2023)","DOI":"10.1016\/j.compag.2023.108106"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Ye, N., et al.: OOD-bench: quantifying and understanding two dimensions of out-of-distribution generalization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7947\u20137958 (2022)","DOI":"10.1109\/CVPR52688.2022.00779"},{"key":"6_CR52","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/TIP.2021.3134142","volume":"31","author":"R Yi","year":"2021","unstructured":"Yi, R., Huang, Y., Guan, Q., Pu, M., Zhang, R.: Learning from pixel-level label noise: a new perspective for semi-supervised semantic segmentation. IEEE Trans. Image Process. 31, 623\u2013635 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"6_CR53","unstructured":"Zhang, J., et al.: OpenOOD v1.5: enhanced benchmark for out-of-distribution detection. In: NeurIPS 2023 Workshop on Distribution Shifts: New Frontiers with Foundation Models (2024)"},{"issue":"8","key":"6_CR54","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, X., He, Y., Xu, R., Yu, H., Shen, Z., Cui, P.: Nico++: towards better benchmarking for domain generalization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16036\u201316047 (2023)","DOI":"10.1109\/CVPR52729.2023.01539"},{"key":"6_CR56","doi-asserted-by":"crossref","unstructured":"Zhao, B., et al.: OOD-CV: a benchmark for robustness to out-of-distribution shifts of individual nuisances in natural images. In: European Conference on Computer Vision, pp. 163\u2013180 (2022)","DOI":"10.1007\/978-3-031-20074-8_10"},{"key":"6_CR57","unstructured":"Zhao, X., et al.: Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)"}],"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\/978-3-031-91672-4_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T15:26:35Z","timestamp":1747754795000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91672-4_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031916717","9783031916724"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91672-4_6","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"}}]}}