{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T16:23:29Z","timestamp":1785428609303,"version":"3.56.0"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198083","type":"print"},{"value":"9783031198090","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19809-0_29","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T07:03:04Z","timestamp":1667199784000},"page":"509-528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["X-Learner: Learning Cross Sources and\u00a0Tasks for\u00a0Universal Visual Representation"],"prefix":"10.1007","author":[{"given":"Yinan","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengshi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianing","family":"Teng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenfei","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"issue":"1","key":"29_CR1","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1093\/imaiai\/iaaa033","volume":"10","author":"A Achille","year":"2021","unstructured":"Achille, A., Paolini, G., Mbeng, G., Soatto, S.: The information complexity of learning tasks, their structure and their distance. Inf. Inference J. IMA 10(1), 51\u201372 (2021)","journal-title":"Inf. Inference J. IMA"},{"key":"29_CR2","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1613\/jair.731","volume":"12","author":"J Baxter","year":"2000","unstructured":"Baxter, J.: A model of inductive bias learning. J. Artif. Intell. Res. 12, 149\u2013198 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"29_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/978-3-540-45167-9_41","volume-title":"Learning Theory and Kernel Machines","author":"S Ben-David","year":"2003","unstructured":"Ben-David, S., Schuller, R.: Exploiting task relatedness for multiple task learning. In: Sch\u00f6lkopf, B., Warmuth, M.K. (eds.) COLT-Kernel 2003. LNCS (LNAI), vol. 2777, pp. 567\u2013580. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-45167-9_41"},{"key":"29_CR4","unstructured":"Bilen, H., Vedaldi, A.: Universal representations: the missing link between faces, text, planktons, and cat breeds. arXiv preprint arXiv:1701.07275 (2017)"},{"key":"29_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1007\/978-3-319-10599-4_29","volume-title":"Computer Vision \u2013 ECCV 2014","author":"L Bossard","year":"2014","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Caesar, H., Uijlings, J., Ferrari, V.: Coco-stuff: thing and stuff classes in context. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1209\u20131218 (2018)","DOI":"10.1109\/CVPR.2018.00132"},{"key":"29_CR7","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. arXiv preprint arXiv:2006.09882 (2020)"},{"issue":"1","key":"29_CR8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R.: Multitask learning. Mach. Learn. 28(1), 41\u201375 (1997)","journal-title":"Multitask learning. Mach. Learn."},{"key":"29_CR9","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017)"},{"key":"29_CR10","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"29_CR11","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"29_CR13","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR14","first-page":"766","volume":"27","author":"A Dosovitskiy","year":"2014","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. Adv. Neural. Inf. Process. Syst. 27, 766\u2013774 (2014)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"29_CR15","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.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88(2), 303\u2013338 (2010). Jun","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR16","unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. In: CVPR workshop, pp. 178\u2013178. IEEE (2004)"},{"key":"29_CR17","unstructured":"Fifty, C., Amid, E., Zhao, Z., Yu, T., Anil, R., Finn, C.: Efficiently identifying task groupings for multi-task learning. arXiv preprint arXiv:2109.04617 (2021)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Gao, Y., Ma, J., Zhao, M., Liu, W., Yuille, A.L.: Nddr-CNN: layerwise feature fusing in multi-task CNNs by neural discriminative dimensionality reduction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3205\u20133214 (2019)","DOI":"10.1109\/CVPR.2019.00332"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Zoph, B., Cubuk, E.D., Le, Q.V., Lin, T.Y.: Multi-task self-training for learning general representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8856\u20138865 (2021)","DOI":"10.1109\/ICCV48922.2021.00873"},{"key":"29_CR20","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the ThirteenthInternational Conference on Artificial Intelligence and Statistic, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"29_CR21","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., Azar, M.G., et al.: Bootstrap your own latent: A new approach to self-supervised learning. arXiv preprint arXiv:2006.07733 (2020)"},{"key":"29_CR22","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Zero-shot detection via vision and language knowledge distillation. arXiv e-prints, pp. arXiv-2104 (2021)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Guo, Y., Li, Y., Wang, L., Rosing, T.: Depthwise convolution is all you need for learning multiple visual domains. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8368\u20138375 (2019)","DOI":"10.1609\/aaai.v33i01.33018368"},{"issue":"11","key":"29_CR24","doi-asserted-by":"publisher","first-page":"2597","DOI":"10.1109\/TPAMI.2017.2738004","volume":"40","author":"H Han","year":"2017","unstructured":"Han, H., Jain, A.K., Wang, F., Shan, S., Chen, X.: Heterogeneous face attribute estimation: a deep multi-task learning approach. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2597\u20132609 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Girshick, R., Doll\u00e1r, P.: Rethinking imagenet pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 4918\u20134927 (2019)","DOI":"10.1109\/ICCV.2019.00502"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"29_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Joulin, A., Van Der Maaten, L., Jabri, A., Vasilache, N.: Learning visual features from large weakly supervised data. In: European Conference on Computer Vision. pp. 67\u201384. Springer (2016)","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"29_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Kornblith, S., Shlens, J., Le, Q.V.: Do better imagenet models transfer better? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2661\u20132671 (2019)","DOI":"10.1109\/CVPR.2019.00277"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"29_CR33","unstructured":"Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)"},{"key":"29_CR34","unstructured":"Kumar, A., Daume III, H.: Learning task grouping and overlap in multi-task learning. arXiv preprint arXiv:1206.6417 (2012)"},{"key":"29_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/978-3-030-65414-6_13","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"W-H Li","year":"2020","unstructured":"Li, W.-H., Bilen, H.: Knowledge distillation for multi-task learning. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12540, pp. 163\u2013176. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-65414-6_13"},{"key":"29_CR36","unstructured":"Li, Z., Ravichandran, A., Fowlkes, C., Polito, M., Bhotika, R., Soatto, S.: Representation consolidation for training expert students. arXiv preprint arXiv:2107.08039 (2021)"},{"key":"29_CR37","unstructured":"Likhosherstov, V., et al: Polyvit: co-training vision transformers on images, videos and audio. arXiv preprint arXiv:2111.12993 (2021)"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"29_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"29_CR40","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1871\u20131880 (2019)","DOI":"10.1109\/CVPR.2019.00197"},{"key":"29_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-01216-8_12","volume-title":"Computer Vision \u2013 ECCV 2018","author":"D Mahajan","year":"2018","unstructured":"Mahajan, D., et al.: Exploring the limits of weakly supervised pretraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 185\u2013201. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_12"},{"key":"29_CR42","unstructured":"Maji, S., Rahtu, E., Kannala, J., Blaschko, M., Vedaldi, A.: Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)"},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Maninis, K.K., Radosavovic, I., Kokkinos, I.: Attentive single-tasking of multiple tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1851\u20131860 (2019)","DOI":"10.1109\/CVPR.2019.00195"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Mensink, T., Uijlings, J., Kuznetsova, A., Gygli, M., Ferrari, V.: Factors of influence for transfer learning across diverse appearance domains and task types. arXiv preprint arXiv:2103.13318 (2021)","DOI":"10.1109\/TPAMI.2021.3129870"},{"key":"29_CR45","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134003 (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"29_CR46","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: A visual vocabulary for flower classification. In: CVPR, vol. 2, pp. 1447\u20131454. IEEE (2006)","DOI":"10.1109\/CVPR.2006.42"},{"key":"29_CR47","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"29_CR48","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"29_CR49","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)"},{"key":"29_CR50","unstructured":"Rebuffi, S.A., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. arXiv preprint arXiv:1705.08045 (2017)"},{"key":"29_CR51","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural. Inf. Process. Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR52","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: Imagenet-21k pretraining for the masses. arXiv preprint arXiv:2104.10972 (2021)"},{"key":"29_CR53","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y.: Fitnets: Hints for thin deep nets. arXiv preprint arXiv:1412.6550 (2014)"},{"issue":"3","key":"29_CR54","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR55","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"key":"29_CR56","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"issue":"2","key":"29_CR57","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/TPAMI.2019.2922181","volume":"42","author":"Z Shen","year":"2019","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., Xue, X.: Object detection from scratch with deep supervision. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 398\u2013412 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"29_CR59","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"29_CR60","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: International Conference on Machine Learning, pp. 1139\u20131147. PMLR (2013)"},{"key":"29_CR61","doi-asserted-by":"crossref","unstructured":"Van Horn, G., Cole, E., Beery, S., Wilber, K., Belongie, S., Mac Aodha, O.: Benchmarking representation learning for natural world image collections. In: CVPR, pp. 12884\u201312893 (2021)","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"29_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., Cai, Z., Gao, D., Vasconcelos, N.: Towards universal object detection by domain attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7289\u20137298 (2019)","DOI":"10.1109\/CVPR.2019.00746"},{"key":"29_CR63","unstructured":"Wang, Z., Tsvetkov, Y., Firat, O., Cao, Y.: Gradient vaccine: investigating and improving multi-task optimization in massively multilingual models. arXiv preprint arXiv:2010.05874 (2020)"},{"issue":"1","key":"29_CR64","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.: Sun database: exploring a large collection of scene categories. IJCV 119(1), 3\u201322 (2016)","journal-title":"IJCV"},{"key":"29_CR65","unstructured":"Yalniz, I.Z., J\u00e9gou, H., Chen, K., Paluri, M., Mahajan, D.: Billion-scale semi-supervised learning for image classification. arXiv preprint arXiv:1905.00546 (2019)"},{"key":"29_CR66","doi-asserted-by":"crossref","unstructured":"Yan, X., Misra, I., Gupta, A., Ghadiyaram, D., Mahajan, D.: Clusterfit: improving generalization of visual representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6509\u20136518 (2020)","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"29_CR67","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Change Loy, C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3973\u20133981 (2015)","DOI":"10.1109\/CVPR.2015.7299023"},{"key":"29_CR68","doi-asserted-by":"crossref","unstructured":"Yang, S., Luo, P., Loy, C.C., Tang, X.: Wider face: a face detection benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5525\u20135533 (2016)","DOI":"10.1109\/CVPR.2016.596"},{"key":"29_CR69","doi-asserted-by":"crossref","unstructured":"Yang, Y., Eriguchi, A., Muzio, A., Tadepalli, P., Lee, S., Hassan, H.: Improving multilingual translation by representation and gradient regularization. arXiv preprint arXiv:2109.04778 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.578"},{"key":"29_CR70","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782 (2020)"},{"key":"29_CR71","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Cheerla, N., Suri, R., Cao, Z., Malik, J., Guibas, L.J.: Robust learning through cross-task consistency. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11197\u201311206 (2020)","DOI":"10.1109\/CVPR42600.2020.01121"},{"key":"29_CR72","doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., Savarese, S.: Taskonomy: disentangling task transfer learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3712\u20133722 (2018)","DOI":"10.1109\/CVPR.2018.00391"},{"key":"29_CR73","doi-asserted-by":"crossref","unstructured":"Zhao, X., Li, H., Shen, X., Liang, X., Wu, Y.: A modulation module for multi-task learning with applications in image retrieval. In: Proceedings of the European Conference on Computer Vision, pp. 401\u2013416 (2018)","DOI":"10.1007\/978-3-030-01246-5_25"},{"key":"29_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-030-58568-6_11","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Zhao","year":"2020","unstructured":"Zhao, X., Schulter, S., Sharma, G., Tsai, Y.-H., Chandraker, M., Wu, Y.: Object detection with a unified label space from multiple datasets. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 178\u2013193. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_11"},{"issue":"6","key":"29_CR75","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2017","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"29_CR76","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Simple multi-dataset detection. arXiv preprint arXiv:2102.13086 (2021)","DOI":"10.1109\/CVPR52688.2022.00742"},{"key":"29_CR78","unstructured":"Zhuang, L., Sun, M., Zhou, T., Gao, H., Darrell, T.: Rethinking the value of network pruning (2018)"},{"issue":"4","key":"29_CR79","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/s41095-020-0184-6","volume":"6","author":"D-N Zou","year":"2020","unstructured":"Zou, D.-N., Zhang, S.-H., Mu, T.-J., Zhang, M.: A new dataset of dog breed images and a benchmark for finegrained classification. Comput. Visual Media 6(4), 477\u2013487 (2020). https:\/\/doi.org\/10.1007\/s41095-020-0184-6","journal-title":"Comput. Visual Media"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19809-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T22:17:58Z","timestamp":1728253078000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19809-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198083","9783031198090"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19809-0_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}