{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:37Z","timestamp":1740123577876,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T00:00:00Z","timestamp":1724803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s11263-024-02104-9","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T06:02:51Z","timestamp":1724824971000},"page":"951-967","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Box Regression and Mask Segmentation Under Long-Tailed Distribution with Gradient Transfusing"],"prefix":"10.1007","volume":"133","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2480-878X","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Xinchao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"key":"2104_CR1","doi-asserted-by":"crossref","unstructured":"Achille, A., Lam, M., Tewari, R., Ravichandran, A., Maji, S., Fowlkes, C.C., Soatto, S. & Perona, P. (2019). Task2vec: Task embedding for meta-learning. In Proceedings of the IEEE\/CVF international conference on computer vision, (pp. 6430\u20136439).","DOI":"10.1109\/ICCV.2019.00653"},{"key":"2104_CR2","doi-asserted-by":"crossref","unstructured":"Alexandridis, K. P., Deng, J., Nguyen, A., & Luo, S. (2022). Long-tailed instance segmentation using gumbel optimized loss. In European conference on computer vision, (pp. 353\u2013369). Springer.","DOI":"10.1007\/978-3-031-20080-9_21"},{"key":"2104_CR3","unstructured":"Byrd, J., & Lipton, Z. (2019). What is the effect of importance weighting in deep learning?. In International conference on machine learning, (pp. 872\u2013881)."},{"key":"2104_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 6154\u20136162).","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2104_CR5","unstructured":"Cao, K., Wei, C., Gaidon, A., Arechiga, N., & Ma, T. (2019) Learning imbalanced datasets with label-distribution-aware margin loss. arXiv preprint arXiv:1906.07413."},{"key":"2104_CR6","unstructured":"Chang, N., Yu, Z., Wang, YX., Anandkumar, A., Fidler, S., & Alvarez, J. M. (2021) Image-level or object-level? a tale of two resampling strategies for long-tailed detection. In International conference on machine learning, PMLR, (pp. 1463\u20131472)."},{"key":"2104_CR7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). Smote: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321\u2013357.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2104_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Pang, J., & Wang, J. et\u00a0al. (2019a). Hybrid task cascade for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 4974\u20134983).","DOI":"10.1109\/CVPR.2019.00511"},{"key":"2104_CR9","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., & Zhang, Z. (2019b) MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"2104_CR10","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T. Y., Song, Y., & Belongie, S. (2019) Class-balanced loss based on effective number of samples. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 9268\u20139277).","DOI":"10.1109\/CVPR.2019.00949"},{"issue":"2","key":"2104_CR11","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., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"2104_CR12","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., & Huang, W. (2021) Exploring classification equilibrium in long-tailed object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, (pp. 3417\u20133426).","DOI":"10.1109\/ICCV48922.2021.00340"},{"key":"2104_CR13","unstructured":"Fiez, T., Chasnov, B., & Ratliff, L. (2020) Implicit learning dynamics in stackelberg games: Equilibria characterization, convergence analysis, and empirical study. In International conference on machine learning, PMLR, (pp. 3133\u20133144)>"},{"key":"2104_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., & Girshick, R. (2019) LVIS: A dataset for large vocabulary instance segmentation. In CVPR","DOI":"10.1109\/CVPR.2019.00550"},{"key":"2104_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"issue":"9","key":"2104_CR16","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263\u20131284.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"2104_CR17","doi-asserted-by":"crossref","unstructured":"Hsieh, T. I., Robb, E., Chen, H. T., & Huang, J. B. (2021) Droploss for long-tail instance segmentation. In Proceedings of the AAAI conference on artificial intelligence, (pp. 1549\u20131557).","DOI":"10.1609\/aaai.v35i2.16246"},{"key":"2104_CR18","doi-asserted-by":"crossref","unstructured":"Hu, X., Jiang, Y., Tang, K., Chen, J., Miao, C., & Zhang, H. (2020). Learning to segment the tail. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 14045\u201314054).","DOI":"10.1109\/CVPR42600.2020.01406"},{"key":"2104_CR19","doi-asserted-by":"crossref","unstructured":"Huang, C., Li, Y., Loy, C. C, & Tang, X. (2016). Learning deep representation for imbalanced classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 5375\u20135384).","DOI":"10.1109\/CVPR.2016.580"},{"issue":"11","key":"2104_CR20","doi-asserted-by":"publisher","first-page":"2781","DOI":"10.1109\/TPAMI.2019.2914680","volume":"42","author":"C Huang","year":"2019","unstructured":"Huang, C., Li, Y., Loy, C. C., & Tang, X. (2019). Deep imbalanced learning for face recognition and attribute prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(11), 2781\u20132794.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2104_CR21","unstructured":"Javaloy, A., & Valera, I. (2021) Rotograd: Gradient homogenization in multitask learning. arXiv preprint arXiv:2103.02631"},{"key":"2104_CR22","unstructured":"Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J., & Kalantidis, Y. (2019). Decoupling representation and classifier for long-tailed recognition. arXiv preprint arXiv:1910.09217"},{"issue":"8","key":"2104_CR23","doi-asserted-by":"publisher","first-page":"3573","DOI":"10.1109\/TNNLS.2017.2732482","volume":"29","author":"SH Khan","year":"2017","unstructured":"Khan, S. H., Hayat, M., Bennamoun, M., et al. (2017). Cost-sensitive learning of deep feature representations from imbalanced data. IEEE Transactions on Neural Networks and Learning Systems, 29(8), 3573\u20133587.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2104_CR24","doi-asserted-by":"publisher","first-page":"81674","DOI":"10.1109\/ACCESS.2020.2991231","volume":"8","author":"B Kim","year":"2020","unstructured":"Kim, B., & Kim, J. (2020). Adjusting decision boundary for class imbalanced learning. IEEE Access, 8, 81674\u201381685.","journal-title":"IEEE Access"},{"issue":"1","key":"2104_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/aos\/1015362183","volume":"30","author":"V Koltchinskii","year":"2002","unstructured":"Koltchinskii, V., & Panchenko, D. (2002). Empirical margin distributions and bounding the generalization error of combined classifiers. The Annals of Statistics, 30(1), 1\u201350.","journal-title":"The Annals of Statistics"},{"key":"2104_CR26","unstructured":"Krishna Menon, A., Jayasumana, S., Singh Rawat, A., Jain, H., Veit, A., & Kumar, S. (2020) Long-tail learning via logit adjustment. arXiv e-prints pp arXiv\u20132007"},{"key":"2104_CR27","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, T., Kang, B., Tang, S., Wang, C., Li, J., & Feng, J. (2020). Overcoming classifier imbalance for long-tail object detection with balanced group softmax. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 10991\u201311000)","DOI":"10.1109\/CVPR42600.2020.01100"},{"key":"2104_CR28","unstructured":"Li, H., Xu, Z., Taylor, G., Studer, C., & Goldstein, T. (2018). Visualizing the loss landscape of neural nets. Advances in Neural Information Processing Systems 31"},{"key":"2104_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, (pp. 2980\u20132988)","DOI":"10.1109\/ICCV.2017.324"},{"key":"2104_CR30","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2104_CR31","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016). Ssd: Single shot multibox detector. In European conference on computer vision, (pp. 21\u201337). Springer.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2104_CR32","doi-asserted-by":"crossref","unstructured":"Mansilla, L., Echeveste, R., Milone, D. H., & Ferrante, E. (2021). Domain generalization via gradient surgery. In Proceedings of the IEEE\/CVF international conference on computer vision, (pp. 6630\u20136638).","DOI":"10.1109\/ICCV48922.2021.00656"},{"key":"2104_CR33","first-page":"2529","volume":"34","author":"TY Pan","year":"2021","unstructured":"Pan, T. Y., Zhang, C., Li, Y., Hu, H., Xuan, D., Changpinyo, S., Gong, B., & Chao, W. L. (2021). On model calibration for long-tailed object detection and instance segmentation. Advances in Neural Information Processing Systems, 34, 2529\u20132542.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2104_CR34","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, (pp. 91\u201399)."},{"key":"2104_CR35","first-page":"4175","volume":"33","author":"J Ren","year":"2020","unstructured":"Ren, J., Yu, C., Ma, X., Zhao, H., & Yi, S. (2020). Balanced meta-softmax for long-tailed visual recognition. Advances in Neural Information Processing Systems, 33, 4175\u20134186.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2104_CR36","doi-asserted-by":"crossref","unstructured":"Shen, L., Lin, Z., & Huang, Q., (2016). Relay backpropagation for effective learning of deep convolutional neural networks. In European conference on computer vision, (pp. 467\u2013482). Springer.","DOI":"10.1007\/978-3-319-46478-7_29"},{"key":"2104_CR37","unstructured":"Shu, J., Xie, Q., Yi, L., Zhao, Q., Zhou, S., Xu, Z., & Meng, D. (2019). Meta-weight-net: Learning an explicit mapping for sample weighting. Advances in Neural Information Processing systems 32."},{"key":"2104_CR38","doi-asserted-by":"crossref","unstructured":"Tan, J., Li, B., Lu, X., Yao, Y., Yu, F., He, T., & Ouyang, W. (2022) The equalization losses: Gradient-driven training for long-tailed object recognition. arXiv preprint arXiv:2210.05566","DOI":"10.1109\/TPAMI.2023.3298433"},{"key":"2104_CR39","doi-asserted-by":"crossref","unstructured":"Tan, J., Lu, X., Zhang, G., Yin, C., & Li, Q. (2021). Equalization loss v2: A new gradient balance approach for long-tailed object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 1685\u20131694)","DOI":"10.1109\/CVPR46437.2021.00173"},{"key":"2104_CR40","unstructured":"Tan, J., Wang, C., Li, Q., & Jan, Y. (2019). Equalization loss for large vocabulary instance segmentation. arXiv preprint arXiv:1911.04692."},{"key":"2104_CR41","doi-asserted-by":"crossref","unstructured":"Tan, J., Wang, C., Li, B., Li, Q., Ouyang, W., Yin, C., & Yan, J. (2020) Equalization loss for long-tailed object recognition. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 11662\u201311671).","DOI":"10.1109\/CVPR42600.2020.01168"},{"issue":"11","key":"2104_CR42","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-sne. Journal of Machine Learning Research, 9(11), 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"2104_CR43","doi-asserted-by":"crossref","unstructured":"Vu, T., Wang, T., Munkhdalai, T., Sordoni, A., Trischler, A., Mattarella-Micke, A., Maji, S., & Iyyer, M. (2020), Exploring and predicting transferability across nlp tasks. arXiv preprint arXiv:2005.00770","DOI":"10.18653\/v1\/2020.emnlp-main.635"},{"key":"2104_CR44","unstructured":"Wang, YX., Ramanan, D., & Hebert, M. (2017). Learning to model the tail. In Advances in neural information processing systems, (pp. 7029\u20137039)."},{"key":"2104_CR45","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, Y., Kang, B., Li, J., Liew, J.H., Tang, S., Hoi, S. & Feng, J. (2019). Classification calibration for long-tail instance segmentation. arXiv preprint arXiv:1910.13081","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"2104_CR46","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, Y., Kang, B., Li, J., Liew, J., Tang, S., Hoi, S., & Feng, J. (2020) The devil is in classification: A simple framework for long-tail instance segmentation. In European conference on computer vision, (pp. 728\u2013744).","DOI":"10.1007\/978-3-030-58568-6_43"},{"key":"2104_CR47","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhang, W., Zang, Y., Cao, Y., Pang, J., Gong, T., Chen, K., Liu, Z., Loy, C.C. & Lin, D. (2021b) Seesaw loss for long-tailed instance segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 9695\u20139704).","DOI":"10.1109\/CVPR46437.2021.00957"},{"key":"2104_CR48","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, Y., Zhao, C., Zeng, W., Wang, J., & Tang, M. (2021c) Adaptive class suppression loss for long-tail object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 3103\u20133112).","DOI":"10.1109\/CVPR46437.2021.00312"},{"issue":"7","key":"2104_CR49","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., & Liu, H. (2018). Additive margin softmax for face verification. IEEE Signal Processing Letters, 25(7), 926\u2013930.","journal-title":"IEEE Signal Processing Letters"},{"key":"2104_CR50","first-page":"6542","volume":"34","author":"J Wang","year":"2021","unstructured":"Wang, J., Wang, K. C., Rudzicz, F., & Brudno, M. (2021). Grad2task: Improved few-shot text classification using gradients for task representation. Advances in Neural Information Processing Systems, 34, 6542\u20136554.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2104_CR51","doi-asserted-by":"crossref","unstructured":"Wu, J., Song, L., Wang, T., Zhang, Q., & Yuan, J. (2020) Forest r-cnn: Large-vocabulary long-tailed object detection and instance segmentation. In Proceedings of the 28th ACM international conference on multimedia, (pp. 1570\u20131578).","DOI":"10.1145\/3394171.3413970"},{"key":"2104_CR52","doi-asserted-by":"crossref","unstructured":"Yin, X., Yu, X., Sohn, K., Liu, X., & Chandraker, M. (2019) Feature transfer learning for face recognition with under-represented data. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 5704\u20135713).","DOI":"10.1109\/CVPR.2019.00585"},{"key":"2104_CR53","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., & Finn, C. (2020). Gradient surgery for multi-task learning. Advances in Neural Information Processing Systems, 33, 5824\u20135836.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2104_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, C., Pan, T.Y., Li, Y., Hu, H., Xuan, D., Changpinyo, S., Gong, B. & Chao, W.L. (2021) Mosaicos: A simple and effective use of object-centric images for long-tailed object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 417\u2013427).","DOI":"10.1109\/ICCV48922.2021.00047"},{"key":"2104_CR55","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B. V. K., & Wang, J. (2018) Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision (ECCV), (pp. 289\u2013305).","DOI":"10.1007\/978-3-030-01219-9_18"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02104-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02104-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02104-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:42:46Z","timestamp":1737528166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02104-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,28]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["2104"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02104-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"type":"print","value":"0920-5691"},{"type":"electronic","value":"1573-1405"}],"subject":[],"published":{"date-parts":[[2024,8,28]]},"assertion":[{"value":"16 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}