{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:39:41Z","timestamp":1778002781709,"version":"3.51.4"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T00:00:00Z","timestamp":1747094400000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s11263-025-02450-2","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T10:53:32Z","timestamp":1747133612000},"page":"5806-5821","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Bamboo: Building Mega-Scale Vision Dataset Continually with Human\u2013Machine Synergy"],"prefix":"10.1007","volume":"133","author":[{"given":"Yuanhan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexin","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,13]]},"reference":[{"key":"2450_CR1","unstructured":"The act partially amending the copyright act (2010) (act no. 52 of 2021; enacted May 2021)."},{"key":"2450_CR2","unstructured":"Barbu, A., Mayo, D., Alverio, J., Luo, W., Wang, C., Gutfreund, D., Tenenbaum, J., & Katz, B. (2019). ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models."},{"key":"2450_CR3","doi-asserted-by":"crossref","unstructured":"Beal, J., Wu, H.-Y., Park, D.\u00a0H., Zhai, A., & Kislyuk, D. (2021). Billion-scale pretraining with vision transformers for multi-task visual representations. arXiv preprint arXiv:2108.05887","DOI":"10.1109\/WACV51458.2022.00150"},{"key":"2450_CR4","unstructured":"Beery, S., Agarwal, A., Cole, E., & Birodkar, V. (2021). The iwildcam 2021 competition dataset. arXiv preprint arXiv:2105.03494"},{"key":"2450_CR5","unstructured":"Ben, H. (2017). Duplicate image detection with perceptual hashing in python. https:\/\/benhoyt.com\/writings\/duplicate-image-detection\/#difference-hash-dhash"},{"key":"2450_CR6","unstructured":"Bommasani, R., Hudson, D.\u00a0A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M.\u00a0S., Bohg, J., Bosselut, A., Brunskill, E., et a. (2021). On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258"},{"key":"2450_CR7","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., & Van\u00a0Gool, L. (2014). Food-101\u2014Mining discriminative components with random forests. In ECCV.","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"2450_CR8","first-page":"59","volume":"27","author":"V Campbell","year":"2016","unstructured":"Campbell, V. (2016). Authors Guild v. Google, Inc. DePaul Journal of Art, Technology & Intellectual Property Law, 27, 59.","journal-title":"DePaul Journal of Art, Technology & Intellectual Property Law"},{"key":"2450_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018). Deep clustering for unsupervised learning of visual features. In ECCV (pp. 132\u2013149).","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"2450_CR10","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882"},{"key":"2450_CR11","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021). Emerging properties in self-supervised vision transformers. arXiv preprint arXiv:2104.14294","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2450_CR12","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., & Soricut, R. (2021). Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"2450_CR13","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In ICML (pp. 1597\u20131607). PMLR."},{"key":"2450_CR14","unstructured":"Chen, X., Fan, H., Girshick, R., & He, K. (2020). Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297"},{"key":"2450_CR15","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In CVPR (pp. 51\u20131258).","DOI":"10.1109\/CVPR.2017.195"},{"key":"2450_CR16","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S. & Vedaldi, A. (2014). Describing textures in the wild. In CVPR.","DOI":"10.1109\/CVPR.2014.461"},{"key":"2450_CR17","unstructured":"Citovsky, G., DeSalvo, G., Gentile, C., Karydas, L., Rajagopalan, A., Rostamizadeh, A., & Kumar, S. (2021). Batch active learning at scale. arXiv preprint arXiv:2107.14263"},{"key":"2450_CR18","unstructured":"Coates, A., Ng, A., & Lee, H. (2011). An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 215\u2013223). JMLR workshop and conference proceedings."},{"key":"2450_CR19","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. In CVPR (pp. 248\u2013255). IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"9","key":"2450_CR20","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/TPAMI.2015.2496141","volume":"38","author":"A Dosovitskiy","year":"2015","unstructured":"Dosovitskiy, A., Fischer, P., Springenberg, J. T., Riedmiller, M., & Brox, T. (2015). Discriminative unsupervised feature learning with exemplar convolutional neural networks. TPAMI, 38(9), 1734\u20131747.","journal-title":"TPAMI"},{"key":"2450_CR21","unstructured":"D\u2019souza, D., Nussbaum, Z., Agarwal, C., & Hooker, S. (2021). A tale of two long tails. arXiv preprint arXiv:2107.13098"},{"key":"2450_CR22","unstructured":"Estimation Lemma. (2010). Estimation Lemma\u2014Wikipedia, the free encyclopedia. [Online; accessed September 29, 2012]."},{"issue":"2","key":"2450_CR23","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010). The Pascal visual object classes (VOC) challenge. IJCV, 88(2), 303\u2013338.","journal-title":"IJCV"},{"key":"2450_CR24","doi-asserted-by":"crossref","unstructured":"Fabian, M. S., Gjergji, K., Gerhard, W., et al.. (2007). Yago: A core of semantic knowledge unifying wordnet and Wikipedia. In WWW (pp. 697\u2013706).","DOI":"10.1145\/1242572.1242667"},{"key":"2450_CR25","doi-asserted-by":"crossref","unstructured":"Fei-Fei, L., Fergus, R., & Perona, P. (2004). Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In CVPR workshop (p. 178). IEEE.","DOI":"10.1109\/CVPR.2004.383"},{"key":"2450_CR26","doi-asserted-by":"crossref","unstructured":"Frome, A., Cheung, G., Abdulkader, A., Zennaro, M., Wu, B., Bissacco, A., Adam, H., Neven, H., & Vincent, L. (2009). Large-scale privacy protection in google street view. In ICCV (pp. 2373\u20132380). IEEE.","DOI":"10.1109\/ICCV.2009.5459413"},{"key":"2450_CR27","unstructured":"Gal, Y. (2016). Uncertainty in deep learning."},{"key":"2450_CR28","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Zoph, B., Cubuk, E.\u00a0D., Le, Q.\u00a0V., & Lin, T.-Y. (2021). Multi-task self-training for learning general representations. arXiv preprint arXiv:2108.11353","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"2450_CR29","unstructured":"Gilad-Bachrach, R., Navot, A., & Tishby, N. (2005). Query by committee made real. In Advances in neural information processing systems, 18."},{"key":"2450_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. In CVPR (pp. 9729\u20139738).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2450_CR31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7","key":"2450_CR32","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., & Borth, D. (2019). EuroSat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7), 2217\u20132226.","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"2450_CR33","unstructured":"Honnibal, M., & Montani, I. (2017). spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing (to appear)."},{"key":"2450_CR34","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, T., Xiong, H., Huan, J., & Dou, D. (2021). Semi-supervised active learning with temporal output discrepancy. In ICCV (pp. 3447\u20133456).","DOI":"10.1109\/ICCV48922.2021.00343"},{"key":"2450_CR35","doi-asserted-by":"crossref","unstructured":"Iglesias, J.\u00a0E., Konukoglu, E., Montillo, A., Tu, Z., & Criminisi, A. (2011). Combining generative and discriminative models for semantic segmentation of CT scans via active learning. In Biennial international conference on information processing in medical imaging (pp. 25\u201336). Springer.","DOI":"10.1007\/978-3-642-22092-0_3"},{"key":"2450_CR36","doi-asserted-by":"crossref","unstructured":"Joshi, A.\u00a0J., Porikli, F., & Papanikolopoulos, N. (2009). Multi-class active learning for image classification. In CVPR (pp. 2372\u20132379). IEEE.","DOI":"10.1109\/CVPRW.2009.5206627"},{"key":"2450_CR37","unstructured":"Kaur, P., Sikka, K., Wang, W., Belongie, S., & Divakaran, A. (2019) Foodx-251: A dataset for fine-grained food classification. arXiv preprint arXiv:1907.06167"},{"key":"2450_CR38","unstructured":"Kendall, A., & Gal, Y. (2017). What uncertainties do we need in Bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977"},{"key":"2450_CR39","doi-asserted-by":"crossref","unstructured":"Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2020). Big transfer (bit): General visual representation learning. In ECCV (pp. 491\u2013507). Springer.","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"2450_CR40","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., & Le, Q.\u00a0V. (2019). Do better ImageNet models transfer better? In CVPR (pp. 2661\u20132671).","DOI":"10.1109\/CVPR.2019.00277"},{"key":"2450_CR41","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., & Fei-Fei, L. (2013). 3d object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia.","DOI":"10.1109\/ICCVW.2013.77"},{"key":"2450_CR42","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images."},{"issue":"7","key":"2450_CR43","doi-asserted-by":"publisher","first-page":"1956","DOI":"10.1007\/s11263-020-01316-z","volume":"128","author":"A Kuznetsova","year":"2020","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Kolesnikov, A., et al. (2020). The open images dataset v4. IJCV, 128(7), 1956\u20131981.","journal-title":"IJCV"},{"key":"2450_CR44","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., & Shakhnarovich, G. (2016). Learning representations for automatic colorization. In ECCV (pp. 577\u2013593). Springer.","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"2450_CR45","unstructured":"Li, J., Zhou, P., Xiong, C., Socher, R., & Hoi, S. C. H. (2020). Prototypical contrastive learning of unsupervised representations. arXiv preprint arXiv:2005.04966"},{"key":"2450_CR46","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.\u00a0L. (2014). Microsoft COCO: Common objects in context. In ECCV (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2450_CR47","unstructured":"Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"2450_CR48","doi-asserted-by":"crossref","unstructured":"Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., & Van Der\u00a0Maaten, L. (2018). Exploring the limits of weakly supervised pretraining. In ECCV (pp. 181\u2013196).","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"2450_CR49","unstructured":"Maji, S., Kannala, J., Rahtu, E., Blaschko, M., & Vedaldi, A. (2013). Fine-grained visual classification of aircraft. Technical report."},{"key":"2450_CR50","volume-title":"WordNet: An electronic lexical database","author":"GA Miller","year":"1998","unstructured":"Miller, G. A. (1998). WordNet: An electronic lexical database. MIT Press."},{"key":"2450_CR51","doi-asserted-by":"crossref","unstructured":"Misra, I., & van\u00a0der Maaten, L. (2020). Self-supervised learning of pretext-invariant representations. In CVPR (pp. 6707\u20136717).","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"2450_CR52","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., & Zisserman, A. (2006). A visual vocabulary for flower classification. In CVPR (Vol.\u00a02, pp. 1447\u20131454). IEEE.","DOI":"10.1109\/CVPR.2006.42"},{"key":"2450_CR53","doi-asserted-by":"crossref","unstructured":"Parkhi, O.\u00a0M., Vedaldi, A., Zisserman, A., & Jawahar, C. V. (2012). Cats and dogs. In CVPR (pp. 3498\u20133505). IEEE.","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"2450_CR54","doi-asserted-by":"crossref","unstructured":"Picek, L., \u0160ulc, M., Matas, J., Heilmann-Clausen, J., Jeppesen, T.\u00a0S., L\u00e6ss\u00f8e, T., & Fr\u00f8slev, T. (2021). Danish fungi 2020\u2013Not just another image recognition dataset. arXiv preprint arXiv:2103.10107","DOI":"10.1109\/WACV51458.2022.00334"},{"key":"2450_CR55","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021). Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020"},{"key":"2450_CR56","doi-asserted-by":"crossref","unstructured":"Roth, D., & Small, K. (2006). Margin-based active learning for structured output spaces. In European conference on machine learning (pp. 413\u2013424). Springer.","DOI":"10.1007\/11871842_40"},{"issue":"3","key":"2450_CR57","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). ImageNet large scale visual recognition challenge. IJCV, 115(3), 211\u2013252.","journal-title":"IJCV"},{"key":"2450_CR58","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., & Komatsuzaki, A. (2021). Laion-400m: Open dataset of clip-filtered 400 million image-text pairs."},{"key":"2450_CR59","unstructured":"Sener, O., & Savarese, S. (2018). Active learning for convolutional neural networks: A core-set approach. In ICLR. OpenReview.net."},{"key":"2450_CR60","unstructured":"Settles, B. (2009). Active learning literature survey."},{"key":"2450_CR61","doi-asserted-by":"crossref","unstructured":"Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., & Sun, J. (2019). Objects365: A large-scale, high-quality dataset for object detection. In ICCV (pp. 8430\u20138439).","DOI":"10.1109\/ICCV.2019.00852"},{"key":"2450_CR62","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017). Revisiting unreasonable effectiveness of data in deep learning era. In ICCV (pp. 843\u2013852).","DOI":"10.1109\/ICCV.2017.97"},{"issue":"10","key":"2450_CR63","doi-asserted-by":"publisher","first-page":"1914","DOI":"10.1109\/TPAMI.2010.106","volume":"32","author":"R Sznitman","year":"2010","unstructured":"Sznitman, R., & Jedynak, B. (2010). Active testing for face detection and localization. TPAMI, 32(10), 1914\u20131920.","journal-title":"TPAMI"},{"key":"2450_CR64","first-page":"583","volume":"12123","author":"TP Tanon","year":"2020","unstructured":"Tanon, T. P., Weikum, G., & Suchanek, F. M. (2020). Yago 4: A reason-able knowledge base. The Semantic Web, 12123, 583\u2013596.","journal-title":"The Semantic Web"},{"issue":"2","key":"2450_CR65","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2812802","volume":"59","author":"B Thomee","year":"2016","unstructured":"Thomee, B., Shamma, D. A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth, D., & Li, L.-J. (2016). Yfcc100m: The new data in multimedia research. Communications of the ACM, 59(2), 64\u201373.","journal-title":"Communications of the ACM"},{"issue":"Nov","key":"2450_CR66","first-page":"45","volume":"2","author":"S Tong","year":"2001","unstructured":"Tong, S., & Koller, D. (2001). Support vector machine active learning with applications to text classification. Journal of Machine Learning Research, 2(Nov), 45\u201366.","journal-title":"Journal of Machine Learning Research"},{"key":"2450_CR67","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., Aodha, O. M., Song, Y., Cui, Y., Sun, C., Shepard, A., Adam, H., Perona, P., & Belongie, S. (2018). The inaturalist species classification and detection dataset. In CVPR (pp. 8769\u20138778).","DOI":"10.1109\/CVPR.2018.00914"},{"key":"2450_CR68","doi-asserted-by":"crossref","unstructured":"Vezhnevets, A., Ferrari, V., & Buhmann, J.\u00a0M. (2012). Weakly supervised structured output learning for semantic segmentation. In CVPR (pp. 845\u2013852). IEEE.","DOI":"10.1109\/CVPR.2012.6247757"},{"issue":"10","key":"2450_CR69","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107, D., & Kr\u00f6tzsch, M. (2014). WikiData: A free collaborative knowledgebase. Communications of the ACM, 57(10), 78\u201385.","journal-title":"Communications of the ACM"},{"key":"2450_CR70","unstructured":"Welinder, P., Branson, S., Mita, T., Wah, C., Schroff, F., Belongie, S., & Perona, P. (2010). Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology."},{"key":"2450_CR71","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xiong, Y., Yu, S.\u00a0X., & Lin, D. (2018). Unsupervised feature learning via non-parametric instance discrimination. In CVPR (pp. 3733\u20133742).","DOI":"10.1109\/CVPR.2018.00393"},{"issue":"7","key":"2450_CR72","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1109\/TGRS.2017.2685945","volume":"55","author":"G-S Xia","year":"2017","unstructured":"Xia, G.-S., Hu, J., Hu, F., Shi, B., Bai, X., Zhong, Y., Zhang, L., & Lu, X. (2017). Aid: A benchmark data set for performance evaluation of aerial scene classification. IEEE Transactions on Geoscience and Remote Sensing, 55(7), 3965\u20133981.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"1","key":"2450_CR73","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-014-0748-y","volume":"119","author":"J Xiao","year":"2016","unstructured":"Xiao, J., Ehinger, K. A., Hays, J., Torralba, A., & Oliva, A. (2016). Sun database: Exploring a large collection of scene categories. IJCV, 119(1), 3\u201322.","journal-title":"IJCV"},{"key":"2450_CR74","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.-T., Hovy, E., & Le, Q.\u00a0V. (2020). Self-training with noisy student improves ImageNet classification. In CVPR (pp. 10687\u201310698).","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"2450_CR75","unstructured":"Yalniz, I.\u00a0Z., J\u00e9gou, H., Chen, K., Paluri, M., & Mahajan, D. (2019). Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546."},{"key":"2450_CR76","doi-asserted-by":"crossref","unstructured":"Yang, K., Qinami, K., Fei-Fei, L., Deng, J., & Russakovsky, O. (2020). Towards fairer datasets: Filtering and balancing the distribution of the people subtree in the ImageNet hierarchy. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency (pp. 547\u2013558).","DOI":"10.1145\/3351095.3375709"},{"key":"2450_CR77","unstructured":"Yang, K., Yau, J., Fei-Fei, L., Deng, J., & Russakovsky, O. (2021). A study of face obfuscation in ImageNet. arXiv preprint arXiv:2103.06191"},{"key":"2450_CR78","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Loy, C. C., & Tang, X. (2015). A large-scale car dataset for fine-grained categorization and verification. In ICCV (pp. 3973\u20133981).","DOI":"10.1109\/CVPR.2015.7299023"},{"issue":"2","key":"2450_CR79","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-014-0781-x","volume":"113","author":"Y Yang","year":"2015","unstructured":"Yang, Y., Ma, Z., Nie, F., Chang, X., & Hauptmann, A. G. (2015). Multi-class active learning by uncertainty sampling with diversity maximization. IJCV, 113(2), 113\u2013127.","journal-title":"IJCV"},{"key":"2450_CR80","doi-asserted-by":"crossref","unstructured":"Yun, S., Oh, S.\u00a0J., Heo, B., Han, D., Choe, J., & Chun, S. (2021). Re-labeling ImageNet: From single to multi-labels, from global to localized labels. arXiv preprint arXiv:2101.05022","DOI":"10.1109\/CVPR46437.2021.00237"},{"key":"2450_CR81","unstructured":"Zhai, X., Puigcerver, J., Kolesnikov, A., Ruyssen, P., Riquelme, C., Lucic, M., Djolonga, J., Pinto, A.\u00a0S., Neumann, M., Dosovitskiy, A., et al. (2019). A large-scale study of representation learning with the visual task adaptation benchmark. arXiv preprint arXiv:1910.04867"},{"key":"2450_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., & Efros, A.\u00a0A. (2016). Colorful image colorization. In ECCV (pp. 649\u2013666). Springer.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"2450_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., & Schiele, B. (2017). Citypersons: A diverse dataset for pedestrian detection. In CVPR, July 2017.","DOI":"10.1109\/CVPR.2017.474"},{"key":"2450_CR84","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A. (2017). Places: A 10 million image database for scene recognition. In TPAMI.","DOI":"10.1167\/17.10.296"},{"key":"2450_CR85","unstructured":"Zoph, B., Ghiasi, G., Lin, T.-Y., Cui, Y., Liu, H., Cubuk, E.\u00a0D., & Le, Q.\u00a0V. (2020). Rethinking pre-training and self-training. arXiv preprint arXiv:2006.06882"},{"key":"2450_CR86","doi-asserted-by":"crossref","unstructured":"Zou, D.-N., Zhang, S.-H., Mu, T.-J., & Zhang, M. (2020). A new dataset of dog breed images and a benchmark for fine-grained classification. Computational Visual Media.","DOI":"10.1007\/s41095-020-0184-6"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02450-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02450-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T14:53:52Z","timestamp":1757170432000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02450-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,13]]},"references-count":86,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["2450"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02450-2","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,13]]},"assertion":[{"value":"23 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}