{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T21:53:38Z","timestamp":1781387618343,"version":"3.54.1"},"reference-count":67,"publisher":"Association for Computing Machinery (ACM)","issue":"11s","license":[{"start":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T00:00:00Z","timestamp":1643587200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2022,1,31]]},"abstract":"<jats:p>Deep learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by leveraging large amounts of data. However, they could fail when the retrieved information is not enough to fit the vast number of parameters, frequently resulting in overfitting and therefore in poor generalizability. Few-Shot Learning aims at designing models that can effectively operate in a scarce data regime, yielding learning strategies that only need few supervised examples to be trained. These procedures are of both practical and theoretical importance, as they are crucial for many real-life scenarios in which data is either costly or even impossible to retrieve. Moreover, they bridge the distance between current data-hungry models and human-like generalization capability. Computer vision offers various tasks that can be few-shot inherent, such as person re-identification. This survey, which to the best of our knowledge is the first tackling this problem, is focused on Few-Shot Object Detection, which has received far less attention compared to Few-Shot Classification due to the intrinsic challenge level. In this regard, this review presents an extensive description of the approaches that have been tested in the current literature, discussing their pros and cons, and classifying them according to a rigorous taxonomy.<\/jats:p>","DOI":"10.1145\/3519022","type":"journal-article","created":{"date-parts":[[2022,2,24]],"date-time":"2022-02-24T14:02:57Z","timestamp":1645711377000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":106,"title":["Few-Shot Object Detection: A Survey"],"prefix":"10.1145","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5230-9689","authenticated-orcid":false,"given":"Simone","family":"Antonelli","sequence":"first","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9437-6217","authenticated-orcid":false,"given":"Danilo","family":"Avola","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9149-2175","authenticated-orcid":false,"given":"Luigi","family":"Cinque","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8180-5203","authenticated-orcid":false,"given":"Donato","family":"Crisostomi","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8425-6892","authenticated-orcid":false,"given":"Gian Luca","family":"Foresti","sequence":"additional","affiliation":[{"name":"Universit\u00e0 degli Studi di Udine, Udine, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1875-7813","authenticated-orcid":false,"given":"Fabio","family":"Galasso","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2540-2570","authenticated-orcid":false,"given":"Marco Raoul","family":"Marini","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1370-8759","authenticated-orcid":false,"given":"Alessio","family":"Mecca","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6446-6473","authenticated-orcid":false,"given":"Daniele","family":"Pannone","sequence":"additional","affiliation":[{"name":"Sapienza Universit\u00e0 degli Studi di Roma, Roma, IT"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,9,9]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.111"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_24"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"e_1_3_1_7_2","first-page":"17","article-title":"Acquiring a single new word","volume":"15","author":"Carey Susan","year":"1978","unstructured":"Susan Carey and E. Bartlett. 1978. Acquiring a single new word. Proceedings of the Stanford Child Language Conference 15 (1978), 17\u201329.","journal-title":"Proceedings of the Stanford Child Language Conference"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2938680"},{"key":"e_1_3_1_10_2","article-title":"Knowledge-aware zero-shot learning: Survey and perspective","author":"Chen Jiaoyan","year":"2021","unstructured":"Jiaoyan Chen, Yuxia Geng, Zhuo Chen, Ian Horrocks, Jeff Z. Pan, and Huajun Chen. 2021. Knowledge-aware zero-shot learning: Survey and perspective. arXiv preprint arXiv:2103.00070 (2021).","journal-title":"arXiv preprint arXiv:2103.00070"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_1_13_2","article-title":"The PASCAL Visual Object Classes Challenge 2012 (VOC2012) results","author":"Everingham M.","year":"2012","unstructured":"M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. 2012. The PASCAL Visual Object Classes Challenge 2012 (VOC2012) results. Retrieved March 5, 2022 from http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html.","journal-title":"http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2012\/workshop\/index.html."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206495"},{"key":"e_1_3_1_16_2","first-page":"1126","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML\u201917)","volume":"70","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning (ICML\u201917), Vol. 70. 1126\u20131135."},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Marian George and Christian Floerkemeier. 2014. Recognizing products: A per-exemplar multi-label image classification approach. In Computer Vision\u2014ECCV 2014 . Lecture Notes in Computer Science Vol. 8690. Springer 440\u2013455.","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"e_1_3_1_21_2","first-page":"1","volume-title":"One-shot object detection with co-attention and co-excitation","author":"Hsieh Ting-I.","year":"2019","unstructured":"Ting-I. Hsieh, Yi-Chen Lo, Hwann-Tzong Chen, and Tyng-Luh Liu. 2019. One-shot object detection with co-attention and co-excitation. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (NIPS\u201919). 1\u201310."},{"key":"e_1_3_1_22_2","article-title":"A survey of deep learning-based object detection","volume":"1907","author":"Jiao Licheng","year":"2019","unstructured":"Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhixi Feng, and Rong Qu. 2019. A survey of deep learning-based object detection. CoRR abs\/1907.09408 (2019).","journal-title":"CoRR"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X16001837"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2013.140"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00512"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Tsung-Yi Lin Michael Maire Serge Belongie James Hays Pietro Perona Deva Ramanan Piotr Doll\u00e1r and C. Lawrence Zitnick. 2014. Microsoft COCO: Common objects in context. In Computer Vision\u2014ECCV 2014 . Lecture Notes in Computer Science Vol. 8693. Springer 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2017.00334"},{"key":"e_1_3_1_32_2","article-title":"Deep learning for generic object detection: A survey","volume":"1809","author":"Liu Li","year":"2018","unstructured":"Li Liu, Wanli Ouyang, Xiaogang Wang, Paul W. Fieguth, Jie Chen, Xinwang Liu, and Matti Pietik\u00e4inen. 2018. Deep learning for generic object detection: A survey. CoRR abs\/1809.02165 (2018).","journal-title":"CoRR"},{"key":"e_1_3_1_33_2","article-title":"SSD: Single shot multibox detector","volume":"1512","author":"Liu Wei","year":"2015","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, and Alexander C. Berg. 2015. SSD: Single shot multibox detector. CoRR abs\/1512.02325 (2015).","journal-title":"CoRR"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_1_35_2","volume-title":"Proceedings of the 2nd International Conference on Learning Representations (ICLR\u201914)","author":"Norouzi Mohammad","year":"2014","unstructured":"Mohammad Norouzi, Tom\u00e1s Mikolov, Samy Bengio, Yoram Singer, Jonathon Shlens, Andrea Frome, Greg Corrado, and Jeffrey Dean. 2014. Zero-shot learning by convex combination of semantic embeddings. In Proceedings of the 2nd International Conference on Learning Representations (ICLR\u201914)."},{"key":"e_1_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Anton Osokin Denis Sumin and Vasily Lomakin. 2020. OS2D: One-stage one-shot object detection by matching anchor features. In Computer Vision\u2014ECCV 2020 . Lecture Notes in Computer Science Vol. 12360. Springer 635\u2013652.","DOI":"10.1007\/978-3-030-58555-6_38"},{"key":"e_1_3_1_37_2","article-title":"Learning with imprinted weights","volume":"1712","author":"Qi Hang","year":"2017","unstructured":"Hang Qi, Matthew Brown, and David G. Lowe. 2017. Learning with imprinted weights. CoRR abs\/1712.07136 (2017).","journal-title":"CoRR"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00618"},{"key":"e_1_3_1_39_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR\u201917)","author":"Ravi Sachin","year":"2017","unstructured":"Sachin Ravi and Hugo Larochelle. 2017. Optimization as a model for few-shot learning. In Proceedings of the 5th International Conference on Learning Representations (ICLR\u201917)."},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_1_42_2","unstructured":"Shaoqing Ren Kaiming He Ross B. Girshick and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS\u201915) . 91\u201399."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2865351"},{"key":"e_1_3_1_44_2","first-page":"2152","volume-title":"Proceedings of the 32nd International Conference on Machine Learning (ICML\u201915)","author":"Romera-Paredes Bernardino","year":"2015","unstructured":"Bernardino Romera-Paredes and Philip H. S. Torr. 2015. An embarrassingly simple approach to zero-shot learning. In Proceedings of the 32nd International Conference on Machine Learning (ICML\u201915). 2152\u20132161."},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_1_46_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Rusu Andrei A.","year":"2019","unstructured":"Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, Oriol Vinyals, Razvan Pascanu, Simon Osindero, and Raia Hadsell. 2019. Meta-learning with latent embedding optimization. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_1_47_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)","author":"Satorras Victor Garcia","year":"2018","unstructured":"Victor Garcia Satorras and Joan Bruna Estrach. 2018. Few-shot learning with graph neural networks. In Proceedings of the 6th International Conference on Learning Representations (ICLR\u201918)."},{"key":"e_1_3_1_48_2","article-title":"RepMet: Representative-based metric learning for classification and one-shot object detection","volume":"1806","author":"Schwartz Eli","year":"2018","unstructured":"Eli Schwartz, Leonid Karlinsky, Joseph Shtok, Sivan Harary, Mattias Marder, Sharathchandra Pankanti, Rog\u00e9rio Schmidt Feris, Abhishek Kumar, Raja Giryes, and Alexander M. Bronstein. 2018. RepMet: Representative-based metric learning for classification and one-shot object detection. CoRR abs\/1806.04728 (2018).","journal-title":"CoRR"},{"key":"e_1_3_1_49_2","first-page":"4077","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS\u201917)","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard S. Zemel. 2017. Prototypical networks for few-shot learning. In Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS\u201917). 4077\u20134087."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"e_1_3_1_51_2","first-page":"3630","volume-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems (NIPS\u201916)","author":"Vinyals Oriol","year":"2016","unstructured":"Oriol Vinyals, Charles Blundell, Tim Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. 2016. Matching networks for one shot learning. In Proceedings of the 29th International Conference on Neural Information Processing Systems (NIPS\u201916). 3630\u20133638."},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/2700292"},{"key":"e_1_3_1_53_2","doi-asserted-by":"crossref","unstructured":"Tao Wang Xiaopeng Zhang Li Yuan and Jiashi Feng. 2019. Few-shot adaptive faster R-CNN. In Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR\u201919) . 7173\u20137182.","DOI":"10.1109\/CVPR.2019.00734"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525858"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01002"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"e_1_3_1_58_2","article-title":"Universal-prototype augmentation for few-shot object detection","volume":"2103","author":"Wu Aming","year":"2021","unstructured":"Aming Wu, Yahong Han, Linchao Zhu, Yi Yang, and Cheng Deng. 2021. Universal-prototype augmentation for few-shot object detection. CoRR abs\/2103.01077 (2021).","journal-title":"CoRR"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_27"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_12"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"e_1_3_1_63_2","first-page":"69","volume-title":"Computer Vision\u2014ECCV 2016","author":"Yu Licheng","year":"2016","unstructured":"Licheng Yu, Patrick Poirson, Shan Yang, Alexander C. Berg, and Tamara L. Berg. 2016. Modeling context in referring expressions. In Computer Vision\u2014ECCV 2016. Lecture Notes in Computer Science, Vol. 9908. Springer, 69\u201385."},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/126"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207417"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.474"},{"key":"e_1_3_1_67_2","article-title":"Semantic relation reasoning for shot-stable few-shot object detection","volume":"2103","author":"Zhu Chenchen","year":"2021","unstructured":"Chenchen Zhu, Fangyi Chen, Uzair Ahmed, Zhiqiang Shen, and Marios Savvides. 2021. Semantic relation reasoning for shot-stable few-shot object detection. CoRR abs\/2103.01903 (2021).","journal-title":"CoRR"},{"key":"e_1_3_1_68_2","article-title":"Object detection in 20 years: A survey","author":"Zou Zhengxia","year":"2019","unstructured":"Zhengxia Zou, Zhenwei Shi, Yuhong Guo, and Jieping Ye. 2019. Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055 (2019).","journal-title":"arXiv preprint arXiv:1905.05055"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3519022","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3519022","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:12:20Z","timestamp":1750191140000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3519022"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,31]]},"references-count":67,"journal-issue":{"issue":"11s","published-print":{"date-parts":[[2022,1,31]]}},"alternative-id":["10.1145\/3519022"],"URL":"https:\/\/doi.org\/10.1145\/3519022","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,31]]},"assertion":[{"value":"2021-07-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}