{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T21:41:54Z","timestamp":1775166114987,"version":"3.50.1"},"publisher-location":"Cham","reference-count":60,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726668","type":"print"},{"value":"9783031726675","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"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\/978-3-031-72667-5_17","type":"book-chapter","created":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T20:11:48Z","timestamp":1727554308000},"page":"297-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Multi-task Learning for\u00a0Few-Shot Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4365-1439","authenticated-orcid":false,"given":"Yan","family":"Ren","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2007-9716","authenticated-orcid":false,"given":"Yanling","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9728-9511","authenticated-orcid":false,"given":"Adams Wai-Kin","family":"Kong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,29]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Wang, G., Qiao, Y.: LSTD: a low-shot transfer detector for object detection. In: AAAI, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Chen, T.I., et al.: Dual-awareness attention for few-shot object detection. IEEE TMM 25, 291\u2013301 (2021)","DOI":"10.1109\/TMM.2021.3125195"},{"key":"17_CR3","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In: International conference on machine learning, pp. 794\u2013803. PMLR (2018)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, B., Wei, Y., Shi, H., Feris, R., Xiong, J., Huang, T.: Revisiting RCNN: on awakening the classification power of faster R-CNN. In: ECCV, pp. 453\u2013468 (2018)","DOI":"10.1007\/978-3-030-01267-0_28"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Clark, K., Luong, M.T., Khandelwal, U., Manning, C.D., Le, Q.V.: Bam! born-again multi-task networks for natural language understanding. arXiv preprint arXiv:1907.04829 (2019)","DOI":"10.18653\/v1\/P19-1595"},{"key":"17_CR6","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: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"17_CR7","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2009","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88, 303\u2013308 (2009)","journal-title":"IJCV"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Fan, Q., Tang, C.K., Tai, Y.W.: Few-shot object detection with model calibration. In: ECCV, pp. 720\u2013739. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19800-7_42","DOI":"10.1007\/978-3-031-19800-7_42"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Han, G., Huang, S., Ma, J., He, Y., Chang, S.F.: Meta faster R-CNN: towards accurate few-shot object detection with attentive feature alignment. In: AAAI, vol. 36, pp. 780\u2013789 (2022)","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"17_CR11","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Hu, H., Bai, S., Li, A., Cui, J., Wang, L.: Dense relation distillation with context-aware aggregation for few-shot object detection. In: CVPR, pp. 10185\u201310194 (2021)","DOI":"10.1109\/CVPR46437.2021.01005"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G., Laradji, I., Vazquez, D., Lacoste-Julien, S., Rodriguez, P.: A survey of self-supervised and few-shot object detection. IEEE TPAMI 45(4), 4071\u20134089 (2022)","DOI":"10.1109\/TPAMI.2022.3199617"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Jung, M.J., Han, S.D., Kim, J.: Re-scoring using image-language similarity for few-shot object detection. Comput. Vis. Image Underst. 241, 103956 (2024)","DOI":"10.1016\/j.cviu.2024.103956"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Kang, B., Liu, Z., Wang, X., Yu, F., Feng, J., Darrell, T.: Few-shot object detection via feature reweighting. In: ICCV, pp. 8420\u20138429 (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Kim, J.U., Kim, S.T., Kim, E.S., Moon, S.K., Ro, Y.M.: Towards high-performance object detection: task-specific design considering classification and localization separation. In: ICASSP, pp. 4317\u20134321. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054600"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Li, A., Li, Z.: Transformation invariant few-shot object detection. In: CVPR, pp. 3094\u20133102 (2021)","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Li, B., Yang, B., Liu, C., Liu, F., Ji, R., Ye, Q.: Beyond max-margin: class margin equilibrium for few-shot object detection. In: CVPR, pp. 7363\u20137372 (2021)","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, Y., Qiang, W., Si, L., Jiao, C., Hu, X., Zheng, C., Sun, F.: Disentangle and remerge: interventional knowledge distillation for few-shot object detection from a conditional causal perspective. In: AAAI, vol.\u00a037, pp. 1323\u20131333 (2023)","DOI":"10.1609\/aaai.v37i1.25216"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Few-shot object detection via classification refinement and distractor retreatment. In: CVPR, pp. 15395\u201315403 (2021)","DOI":"10.1109\/CVPR46437.2021.01514"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: ECCV, pp. 740\u2013755. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"17_CR22","first-page":"18878","volume":"34","author":"B Liu","year":"2021","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P., Liu, Q.: Conflict-averse gradient descent for multi-task learning. NeurIPS 34, 18878\u201318890 (2021)","journal-title":"NeurIPS"},{"key":"17_CR23","unstructured":"Liu, L., et al.: Towards impartial multi-task learning. In: ICLR (2020)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., Liang, Y., Gitter, A.: Loss-balanced task weighting to reduce negative transfer in multi-task learning. In: AAAI, vol.\u00a033, pp. 9977\u20139978 (2019)","DOI":"10.1609\/aaai.v33i01.33019977"},{"key":"17_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Lu, X., Diao, W., Mao, Y., Li, J., Wang, P., Sun, X., Fu, K.: Breaking immutable: information-coupled prototype elaboration for few-shot object detection. In: AAAI, vol.\u00a037, pp. 1844\u20131852 (2023)","DOI":"10.1609\/aaai.v37i2.25274"},{"issue":"1","key":"17_CR27","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/TCYB.2022.3149825","volume":"53","author":"Y Lu","year":"2022","unstructured":"Lu, Y., Chen, X., Wu, Z., Yu, J.: Decoupled metric network for single-stage few-shot object detection. IEEE Trans. Cybern. 53(1), 514\u2013525 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Ma, J., Zhao, Z., Yi, X., Chen, J., Hong, L., Chi, E.H.: Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, pp. 1930\u20131939 (2018)","DOI":"10.1145\/3219819.3220007"},{"key":"17_CR29","doi-asserted-by":"publisher","unstructured":"Ma, J., Han, G., Huang, S., Yang, Y., Chang, S.F.: Few-shot end-to-end object detection via constantly concentrated encoding across heads. In: ECCV, pp. 57\u201373. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_4","DOI":"10.1007\/978-3-031-19809-0_4"},{"key":"17_CR30","unstructured":"Navon, A., et al.: Multi-task learning as a bargaining game. arXiv preprint arXiv:2202.01017 (2022)"},{"issue":"10","key":"17_CR31","doi-asserted-by":"publisher","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","volume":"43","author":"K Oksuz","year":"2020","unstructured":"Oksuz, K., Cam, B.C., Kalkan, S., Akbas, E.: Imbalance problems in object detection: a review. IEEE TPAMI 43(10), 3388\u20133415 (2020)","journal-title":"IEEE TPAMI"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Qiao, L., Zhao, Y., Li, Z., Qiu, X., Wu, J., Zhang, C.: DeFRCN: decoupled faster R-CNN for few-shot object detection. In: ICCV, pp. 8681\u20138690 (2021)","DOI":"10.1109\/ICCV48922.2021.00856"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Quan, Q., Yao, Q., Li, J., Zhou, S.K.: Which images to label for few-shot medical landmark detection? In: CVPR, pp. 20606\u201320616 (2022)","DOI":"10.1109\/CVPR52688.2022.01995"},{"key":"17_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: CVPR, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"17_CR36","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. NeurIPS 28 (2015)"},{"key":"17_CR37","unstructured":"Rusu, A.A., et al.: Policy distillation. arXiv preprint arXiv:1511.06295 (2015)"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Song, G., Liu, Y., Wang, X.: Revisiting the sibling head in object detector. In: CVPR, pp. 11563\u201311572 (2020)","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Song, H., Dong, L., Zhang, W.N., Liu, T., Wei, F.: CLIP models are few-shot learners: Empirical studies on VQA and visual entailment. arXiv preprint arXiv:2203.07190 (2022)","DOI":"10.18653\/v1\/2022.acl-long.421"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Sun, B., Li, B., Cai, S., Yuan, Y., Zhang, C.: FSCE: few-shot object detection via contrastive proposal encoding. In: CVPR, pp. 7352\u20137362 (2021)","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"17_CR41","unstructured":"Wang, X., Huang, T., Gonzalez, J., Darrell, T., Yu, F.: Frustratingly simple few-shot object detection. In: International Conference on Machine Learning, pp. 9919\u20139928. PMLR (2020)"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Meta-learning to detect rare objects. In: ICCV, pp. 9925\u20139934 (2019)","DOI":"10.1109\/ICCV.2019.01002"},{"key":"17_CR43","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)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Wertheimer, D., Hariharan, B.: Few-shot learning with localization in realistic settings. In: CVPR, pp. 6558\u20136567 (2019)","DOI":"10.1109\/CVPR.2019.00672"},{"key":"17_CR45","doi-asserted-by":"publisher","unstructured":"Wu, J., Liu, S., Huang, D., Wang, Y.: Multi-scale positive sample refinement for few-shot object detection. In: ECCV, pp. 456\u2013472. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_27","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, Y., Yuan, L., Liu, Z., Wang, L., Li, H., Fu, Y.: Rethinking classification and localization for object detection. In: CVPR, pp. 10186\u201310195 (2020)","DOI":"10.1109\/CVPR42600.2020.01020"},{"issue":"3","key":"17_CR47","first-page":"3090","volume":"45","author":"Y Xiao","year":"2022","unstructured":"Xiao, Y., Lepetit, V., Marlet, R.: Few-shot object detection and viewpoint estimation for objects in the wild. IEEE TPAMI 45(3), 3090\u20133106 (2022)","journal-title":"IEEE TPAMI"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Xu, J., Le, H., Samaras, D.: Generating features with increased crop-related diversity for few-shot object detection. In: CVPR, pp. 19713\u201319722 (2023)","DOI":"10.1109\/CVPR52729.2023.01888"},{"key":"17_CR49","doi-asserted-by":"crossref","unstructured":"Yan, X., Chen, Z., Xu, A., Wang, X., Liang, X., Lin, L.: Meta R-CNN: towards general solver for instance-level low-shot learning. In: ICCV, pp. 9577\u20139586 (2019)","DOI":"10.1109\/ICCV.2019.00967"},{"key":"17_CR50","first-page":"3521","volume":"33","author":"Y Yang","year":"2020","unstructured":"Yang, Y., Wei, F., Shi, M., Li, G.: Restoring negative information in few-shot object detection. NeurIPS 33, 3521\u20133532 (2020)","journal-title":"NeurIPS"},{"key":"17_CR51","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. NeurIPS 33, 5824\u20135836 (2020)","journal-title":"NeurIPS"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, G., Cui, K., Wu, R., Lu, S., Tian, Y.: PNPDet: efficient few-shot detection without forgetting via plug-and-play sub-networks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3823\u20133832 (2021)","DOI":"10.1109\/WACV48630.2021.00387"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, G., Luo, Z., Cui, K., Lu, S., Xing, E.P.: Meta-DETR: image-level few-shot detection with inter-class correlation exploitation. IEEE TPAMI 45(11), 12832\u201312843 (2022)","DOI":"10.1109\/TPAMI.2022.3195735"},{"key":"17_CR54","doi-asserted-by":"publisher","unstructured":"Zhang, R., Zhang, W., Fang, R., Gao, P., Li, K., Dai, J., Qiao, Y., Li, H.: Tip-adapter: training-free adaption of clip for few-shot classification. In: ECCV, pp. 493\u2013510. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, S., Wang, L., Murray, N., Koniusz, P.: Kernelized few-shot object detection with efficient integral aggregation. In: CVPR, pp. 19207\u201319216 (2022)","DOI":"10.1109\/CVPR52688.2022.01861"},{"issue":"12","key":"17_CR56","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Trans. Knowl. Data Eng. 34(12), 5586\u20135609 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"17_CR57","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: ECCV, pp. 94\u2013108. Springer (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_7","DOI":"10.1007\/978-3-319-10599-4_7"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Zhao, B., Cui, Q., Song, R., Qiu, Y., Liang, J.: Decoupled knowledge distillation. In: CVPR, pp. 11953\u201311962 (2022)","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"17_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, C., Chen, F., Ahmed, U., Shen, Z., Savvides, M.: Semantic relation reasoning for shot-stable few-shot object detection. In: CVPR, pp. 8782\u20138791 (2021)","DOI":"10.1109\/CVPR46437.2021.00867"},{"key":"17_CR60","doi-asserted-by":"crossref","unstructured":"Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey. Proc. IEEE 111(3), 257\u2013276 (2023)","DOI":"10.1109\/JPROC.2023.3238524"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72667-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:08:24Z","timestamp":1732828104000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72667-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,29]]},"ISBN":["9783031726668","9783031726675"],"references-count":60,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72667-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,29]]},"assertion":[{"value":"29 September 2024","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"}}]}}