{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T17:54:48Z","timestamp":1793987688364,"version":"4.8.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734106","type":"print"},{"value":"9783031734113","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-73411-3_20","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T20:07:07Z","timestamp":1732306027000},"page":"350-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["SMILe: Leveraging Submodular Mutual Information For Robust Few-Shot Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0189-8310","authenticated-orcid":false,"given":"Anay","family":"Majee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4871-8085","authenticated-orcid":false,"given":"Ryan","family":"Sharp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9851-463X","authenticated-orcid":false,"given":"Rishabh","family":"Iyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, A., Majee, A., Subramanian, A., Arora, C.: Attention guided cosine margin to overcome class-imbalance in few-shot road object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, pp. 221\u2013230 (2022)","DOI":"10.1109\/WACVW54805.2022.00028"},{"key":"20_CR2","unstructured":"Cao, Y., et al.: Few-shot object detection via association and discrimination. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Wang, G., Qiao, Y.: LSTD: a low-shot transfer detector for object detection. In: AAAI, pp. 2836\u20132843 (2018)","DOI":"10.1609\/aaai.v32i1.11716"},{"key":"20_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","DOI":"10.1007\/s11263-009-0275-4"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Fan, Q., Zhuo, W., Tang, C.K., Tai, Y.W.: Few-shot object detection with attention-RPN and multi-relation detector. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, Y., Li, Z., Sun, J.: Generalized few-shot object detection without forgetting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4527\u20134536 (2021)","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, Y., Li, Z., Sun, J.: Generalized few-shot object detection without forgetting (2021)","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"20_CR9","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML (2017)"},{"key":"20_CR10","unstructured":"Fujishige, S.: Submodular Functions and Optimization, vol.\u00a058. Elsevier, Amsterdam (2005)"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Gidaris, S., Komodakis, N.: Dynamic few-shot visual learning without forgetting. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00459"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R.B.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Han, G., Ma, J., Huang, S., Chen, L., Chang, S.F.: Few-shot object detection with fully cross-transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5321\u20135330 (2022)","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Jegelka, S., Bilmes, J.: Submodularity beyond submodular energies: coupling edges in graph cuts. In: CVPR 2011 (2011)","DOI":"10.1109\/CVPR.2011.5995589"},{"key":"20_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 (2019)","DOI":"10.1109\/ICCV.2019.00851"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Karlinsky, L., et al.: RepMet: representative-based metric learning for classification and few-shot object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00534"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Kaul, P., Xie, W., Zisserman, A.: Label, verify, correct: a simple few-shot object detection method. In: IEEE Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Kaushal, V., et al.: Demystifying multi-faceted video summarization: tradeoff between diversity, representation, coverage and importance. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 452\u2013461 (2019)","DOI":"10.1109\/WACV.2019.00054"},{"key":"20_CR19","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: Advances in Neural Information Processing Systems (2020)"},{"key":"20_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-19839-7_1","volume-title":"Computer Vision - ECCV 2022","author":"S Kothawade","year":"2022","unstructured":"Kothawade, S., Ghosh, S., Shekhar, S., Xiang, Y., Iyer, R.K.: Talisman: targeted active learning for object detection with rare classes and slices using submodular mutual information. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 1\u201316. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_1"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Kothawade, S., Kaushal, V., Ramakrishnan, G., Bilmes, J.A., Iyer, R.K.: PRISM: a rich class of parameterized submodular information measures for guided data subset selection. In: Thirty-Sixth AAAI Conference on Artificial Intelligence. AAAI, pp. 10238\u201310246 (2022)","DOI":"10.1609\/aaai.v36i9.21264"},{"key":"20_CR22","unstructured":"Li, B., Liu, C., Shi, M., Chen, X., Ji, X., Ye, Q.: Proposal distribution calibration for few-shot object detection. IEEE Trans. Neural Netw. Learn. Syst. (2022)"},{"key":"20_CR23","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 (2021)","DOI":"10.1109\/CVPR46437.2021.00728"},{"key":"20_CR24","unstructured":"Lin, H., Bilmes, J.: A class of submodular functions for document summarization. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (2011)"},{"key":"20_CR25","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":"20_CR26","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Integrally migrating pre-trained transformer encoder-decoders for visual object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6825\u20136834 (2023)","DOI":"10.1109\/ICCV51070.2023.00628"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Ma, J., Niu, Y., Xu, J., Huang, S., Han, G., Chang, S.F.: Digeo: discriminative geometry-aware learning for generalized few-shot object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00313"},{"key":"20_CR28","unstructured":"Majee, A., Agrawal, K., Subramanian, A.: Few-shot learning for road object detection. In: AAAI Workshop on Meta-learning and MetaDL Challenge, vol.\u00a0140, pp. 115\u2013126 (2021)"},{"key":"20_CR29","unstructured":"Majee, A., Kothawade, S.N., Killamsetty, K., Iyer, R.K.: SCoRe: submodular combinatorial Representation Learning. In: Forty-First International Conference on Machine Learning (ICML) (2024)"},{"key":"20_CR30","unstructured":"Ren, S., He, K., Girshick, R.B., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. (2015)"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Shangguan, Z., Rostami, M.: Identification of novel classes for improving few-shot object detection (2023)","DOI":"10.1109\/ICCVW60793.2023.00360"},{"key":"20_CR32","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS, pp. 4077\u20134087 (2017)"},{"key":"20_CR33","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 (2021)","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning To compare: relation network for few-shot learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"20_CR35","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., Wierstra, D.: Matching networks for one shot learning. In: NeurIPS (2016)"},{"key":"20_CR36","unstructured":"Wang, X., Huang, T.E., Darrell, T., Gonzalez, J.E., Yu, F.: Frustratingly simple few-shot object detection. In: ICML (2020)"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Ramanan, D., Hebert, M.: Meta-learning to detect rare objects. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01002"},{"key":"20_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-030-58517-4_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wu","year":"2020","unstructured":"Wu, J., Liu, S., Huang, D., Wang, Y.: Multi-scale positive sample refinement for few-shot object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 456\u2013472. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_27"},{"key":"20_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1007\/978-3-030-58520-4_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Xiao","year":"2020","unstructured":"Xiao, Y., Marlet, R.: Few-shot object detection and viewpoint estimation for objects in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 192\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_12"},{"key":"20_CR40","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: CVPR, pp. 9577\u20139586 (2019)","DOI":"10.1109\/ICCV.2019.00967"},{"key":"20_CR41","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: WACV, pp. 3823\u20133832 (2021)","DOI":"10.1109\/WACV48630.2021.00387"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhou, S., Guan, J., Zhang, J.: Accurate few-shot object detection with support-query mutual guidance and hybrid loss. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01419"},{"key":"20_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-69538-5_23","volume-title":"Computer Vision \u2013 ACCV 2020","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Luo, D., Wang, L., Koniusz, P.: Few-shot object detection by second-order pooling. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12625, pp. 369\u2013387. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69538-5_23"},{"key":"20_CR44","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 (2021)","DOI":"10.1109\/CVPR46437.2021.00867"}],"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\/978-3-031-73411-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T21:25:50Z","timestamp":1732310750000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73411-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031734106","9783031734113"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73411-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 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"}}]}}