{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T16:13:25Z","timestamp":1758125605247,"version":"3.40.4"},"reference-count":65,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,5,16]],"date-time":"2024-05-16T00:00:00Z","timestamp":1715817600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["High-Confidence Computing"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1016\/j.hcc.2024.100237","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T07:45:41Z","timestamp":1716450341000},"page":"100237","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"title":["Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners"],"prefix":"10.1016","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7846-5472","authenticated-orcid":false,"given":"Yuantao","family":"Yin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xue","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siqing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"year":"2021","series-title":"What is considered complete for visual recognition?","author":"Xie","key":"10.1016\/j.hcc.2024.100237_b1"},{"key":"10.1016\/j.hcc.2024.100237_b2","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2019-June","first-page":"5351","article-title":"Lvis: A dataset for large vocabulary instance segmentation","author":"Gupta","year":"2019"},{"issue":"6266","key":"10.1016\/j.hcc.2024.100237_b3","doi-asserted-by":"crossref","first-page":"1332","DOI":"10.1126\/science.aab3050","article-title":"Human-level concept learning through probabilistic program induction","volume":"350","author":"Lake","year":"2015","journal-title":"Science"},{"key":"10.1016\/j.hcc.2024.100237_b4","unstructured":"J.D.M.-W.C. Kenton, L.K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in: Proceedings of NAACL-HLT, 2019, pp. 4171\u20134186."},{"key":"10.1016\/j.hcc.2024.100237_b5","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b6","doi-asserted-by":"crossref","unstructured":"T. Schick, H. Sch\u00fctze, It\u2019s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners, in: NAACL-HLT, 2021.","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"10.1016\/j.hcc.2024.100237_b7","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.hcc.2024.100237_b8","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b9","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.hcc.2024.100237_b10","doi-asserted-by":"crossref","unstructured":"P. Sun, R. Zhang, Y. Jiang, T. Kong, C. Xu, W. Zhan, M. Tomizuka, L. Li, Z. Yuan, C. Wang, et al., Sparse r-cnn: End-to-end object detection with learnable proposals, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14454\u201314463.","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"10.1016\/j.hcc.2024.100237_b11","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable Transformers for End-to-End Object Detection, in: International Conference on Learning Representations, 2020."},{"year":"2022","series-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","key":"10.1016\/j.hcc.2024.100237_b12"},{"key":"10.1016\/j.hcc.2024.100237_b13","doi-asserted-by":"crossref","unstructured":"S. Shao, Z. Li, T. Zhang, C. Peng, G. Yu, X. Zhang, J. Li, J. Sun, Objects365: A large-scale, high-quality dataset for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8430\u20138439.","DOI":"10.1109\/ICCV.2019.00852"},{"key":"10.1016\/j.hcc.2024.100237_b14","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b15","unstructured":"O. Sim\u00e9oni, G. Puy, H.V. Vo, S. Roburin, S. Gidaris, A. Bursuc, P. P\u00e9rez, R. Marlet, J. Ponce, Localizing Objects with Self-Supervised Transformers and no Labels, in: BMVC-British Machine Vision Conference, 2021."},{"key":"10.1016\/j.hcc.2024.100237_b16","unstructured":"S.X. Hu, D. Li, J. St\u00fchmer, M. Kim, T.M. Hospedales, Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9068\u20139077."},{"key":"10.1016\/j.hcc.2024.100237_b17","article-title":"Meta-DETR: Image-level few-shot detection with inter-class correlation exploitation","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.hcc.2024.100237_b18","unstructured":"A. Kumar, A. Raghunathan, R.M. Jones, T. Ma, P. Liang, Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution, in: International Conference on Learning Representations, 2021."},{"year":"2021","series-title":"Combined scaling for zero-shot transfer learning","author":"Pham","key":"10.1016\/j.hcc.2024.100237_b19"},{"key":"10.1016\/j.hcc.2024.100237_b20","doi-asserted-by":"crossref","unstructured":"M. Wortsman, G. Ilharco, J.W. Kim, M. Li, S. Kornblith, R. Roelofs, R.G. Lopes, H. Hajishirzi, A. Farhadi, H. Namkoong, et al., Robust fine-tuning of zero-shot models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 7959\u20137971.","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"10.1016\/j.hcc.2024.100237_b21","unstructured":"Y. Lee, A.S. Chen, F. Tajwar, A. Kumar, H. Yao, P. Liang, C. Finn, Surgical Fine-Tuning Improves Adaptation to Distribution Shifts, in: NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications."},{"key":"10.1016\/j.hcc.2024.100237_b22","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.hcc.2024.100237_b23","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.hcc.2024.100237_b24","series-title":"Learning from very few samples: A survey","first-page":"1","author":"Lu","year":"2020"},{"key":"10.1016\/j.hcc.2024.100237_b25","series-title":"A survey of self-supervised and few-shot object detection","first-page":"1","author":"Huang","year":"2021"},{"key":"10.1016\/j.hcc.2024.100237_b26","first-page":"4078","article-title":"Prototypical networks for few-shot learning","volume":"2017-December","author":"Snell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b27","first-page":"3637","article-title":"Matching networks for one shot learning","author":"Vinyals","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b28","series-title":"34th International Conference on Machine Learning, Vol. 3","first-page":"1856","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.hcc.2024.100237_b29","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"8805","article-title":"Few-shot learning via embedding adaptation with set-to-set functions","author":"Ye","year":"2020"},{"key":"10.1016\/j.hcc.2024.100237_b30","doi-asserted-by":"crossref","unstructured":"Y.-X. Wang, R. Girshick, M. Hebert, B. Hariharan, Low-shot learning from imaginary data, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7278\u20137286.","DOI":"10.1109\/CVPR.2018.00760"},{"key":"10.1016\/j.hcc.2024.100237_b31","doi-asserted-by":"crossref","unstructured":"J. Wu, T. Zhang, Y. Zhang, F. Wu, Task-Aware Part Mining Network for Few-Shot Learning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 8433\u20138442.","DOI":"10.1109\/ICCV48922.2021.00832"},{"key":"10.1016\/j.hcc.2024.100237_b32","doi-asserted-by":"crossref","unstructured":"Y. Zou, S. Zhang, K. Chen, Y. Tian, Y. Wang, J.M. Moura, Compositional few-shot recognition with primitive discovery and enhancing, in: Proceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 156\u2013164.","DOI":"10.1145\/3394171.3413849"},{"key":"10.1016\/j.hcc.2024.100237_b33","series-title":"European Conference on Computer Vision","first-page":"491","article-title":"Big transfer (bit): General visual representation learning","author":"Kolesnikov","year":"2020"},{"key":"10.1016\/j.hcc.2024.100237_b34","series-title":"9th International Conference on Learning Representations","article-title":"An image is worth 16\u00a0\u00d7\u00a016 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"year":"2021","series-title":"Florence: A new foundation model for computer vision","author":"Yuan","key":"10.1016\/j.hcc.2024.100237_b35"},{"key":"10.1016\/j.hcc.2024.100237_b36","series-title":"Proceedings of the IEEE International Conference on Computer Vision, Vol. 2019-October","first-page":"8419","article-title":"Few-shot object detection via feature reweighting","author":"Kang","year":"2019"},{"key":"10.1016\/j.hcc.2024.100237_b37","series-title":"Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2017-January","first-page":"6517","article-title":"YOLO9000: Better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.1016\/j.hcc.2024.100237_b38","series-title":"Proceedings of the IEEE International Conference on Computer Vision, Vol. 2019-October","first-page":"9576","article-title":"Meta R-CNN: Towards general solver for instance-level low-shot learning","author":"Yan","year":"2019"},{"key":"10.1016\/j.hcc.2024.100237_b39","series-title":"European Conference on Computer Vision","first-page":"192","article-title":"Few-shot object detection and viewpoint estimation for objects in the wild","author":"Xiao","year":"2020"},{"year":"2021","series-title":"Meta-detr: Few-shot object detection via unified image-level meta-learning","author":"Zhang","key":"10.1016\/j.hcc.2024.100237_b40"},{"key":"10.1016\/j.hcc.2024.100237_b41","unstructured":"X. Wang, T.E. Huang, T. Darrell, J.E. Gonzalez, F. Yu, Frustratingly simple few-shot object detection, in: 37th International Conference on Machine Learning, Vol. PartF168147-13, ICML 2020, 2020, pp. 9861\u20139870."},{"key":"10.1016\/j.hcc.2024.100237_b42","series-title":"ICCV2021","article-title":"DeFRCN: Decoupled faster R-CNN for few-shot object detection","author":"Qiao","year":"2021"},{"key":"10.1016\/j.hcc.2024.100237_b43","article-title":"Few-shot object detection via association and discrimination","volume":"34","author":"Cao","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.hcc.2024.100237_b44","doi-asserted-by":"crossref","unstructured":"T.-Y. Lin, P. Doll\u00e1r, R. Girshick, K. He, B. Hariharan, S. Belongie, Feature pyramid networks for object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"10.1016\/j.hcc.2024.100237_b45","doi-asserted-by":"crossref","unstructured":"Y. Zhong, J. Yang, P. Zhang, C. Li, N. Codella, L.H. Li, L. Zhou, X. Dai, L. Yuan, Y. Li, et al., Regionclip: Region-based language-image pretraining, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16793\u201316803.","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"10.1016\/j.hcc.2024.100237_b46","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.hcc.2024.100237_b47","doi-asserted-by":"crossref","unstructured":"A. Achille, M. Lam, R. Tewari, A. Ravichandran, S. Maji, C.C. Fowlkes, S. Soatto, P. Perona, Task2vec: Task embedding for meta-learning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6430\u20136439.","DOI":"10.1109\/ICCV.2019.00653"},{"key":"10.1016\/j.hcc.2024.100237_b48","series-title":"European Conference on Computer Vision","first-page":"57","article-title":"Few-shot end-to-end object detection via constantly concentrated encoding across heads","author":"Ma","year":"2022"},{"key":"10.1016\/j.hcc.2024.100237_b49","series-title":"International Workshop on Multiple Classifier Systems","first-page":"1","article-title":"Ensemble methods in machine learning","author":"Dietterich","year":"2000"},{"issue":"2","key":"10.1016\/j.hcc.2024.100237_b50","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"year":"2022","series-title":"CD-FSOD: A benchmark for cross-domain few-shot object detection","author":"Xiong","key":"10.1016\/j.hcc.2024.100237_b51"},{"key":"10.1016\/j.hcc.2024.100237_b52","series-title":"European Conference on Computer Vision","first-page":"366","article-title":"Rethinking few-shot object detection on a multi-domain benchmark","author":"Lee","year":"2022"},{"key":"10.1016\/j.hcc.2024.100237_b53","doi-asserted-by":"crossref","unstructured":"Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, S. Lin, B. Guo, Swin transformer: Hierarchical vision transformer using shifted windows, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.hcc.2024.100237_b54","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.hcc.2024.100237_b55","series-title":"European Conference on Computer Vision","first-page":"456","article-title":"Multi-scale positive sample refinement for few-shot object detection","author":"Wu","year":"2020"},{"key":"10.1016\/j.hcc.2024.100237_b56","doi-asserted-by":"crossref","unstructured":"G. Han, S. Huang, J. Ma, Y. He, S.-F. Chang, Meta faster r-cnn: Towards accurate few-shot object detection with attentive feature alignment, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36, No. 1, 2022, pp. 780\u2013789.","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"10.1016\/j.hcc.2024.100237_b57","series-title":"European Conference on Computer Vision","first-page":"578","article-title":"Multi-faceted distillation of base-novel commonality for few-shot object detection","author":"Wu","year":"2022"},{"key":"10.1016\/j.hcc.2024.100237_b58","doi-asserted-by":"crossref","unstructured":"X. Yan, Z. Chen, A. Xu, X. Wang, X. Liang, L. Lin, Meta r-cnn: Towards general solver for instance-level low-shot learning, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9577\u20139586.","DOI":"10.1109\/ICCV.2019.00967"},{"key":"10.1016\/j.hcc.2024.100237_b59","article-title":"Dual-awareness attention for few-shot object detection","author":"Chen","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.hcc.2024.100237_b60","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"10180","article-title":"Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection","author":"Hu","year":"2021"},{"key":"10.1016\/j.hcc.2024.100237_b61","doi-asserted-by":"crossref","unstructured":"A. Li, Z. Li, Transformation invariant few-shot object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3094\u20133102.","DOI":"10.1109\/CVPR46437.2021.00311"},{"key":"10.1016\/j.hcc.2024.100237_b62","doi-asserted-by":"crossref","unstructured":"C. Zhu, F. Chen, U. Ahmed, Z. Shen, M. Savvides, Semantic relation reasoning for shot-stable few-shot object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8782\u20138791.","DOI":"10.1109\/CVPR46437.2021.00867"},{"year":"2021","series-title":"Label, verify, correct: A simple few shot object detection method","author":"Kaul","key":"10.1016\/j.hcc.2024.100237_b63"},{"key":"10.1016\/j.hcc.2024.100237_b64","series-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition","first-page":"7348","article-title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","author":"Sun","year":"2021"},{"key":"10.1016\/j.hcc.2024.100237_b65","doi-asserted-by":"crossref","unstructured":"Z. Liu, H. Hu, Y. Lin, Z. Yao, Z. Xie, Y. Wei, J. Ning, Y. Cao, Z. Zhang, L. Dong, et al., Swin transformer v2: Scaling up capacity and resolution, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 12009\u201312019.","DOI":"10.1109\/CVPR52688.2022.01170"}],"container-title":["High-Confidence Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667295224000400?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2667295224000400?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T21:18:18Z","timestamp":1745011098000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2667295224000400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["S2667295224000400"],"URL":"https:\/\/doi.org\/10.1016\/j.hcc.2024.100237","relation":{},"ISSN":["2667-2952"],"issn-type":[{"type":"print","value":"2667-2952"}],"subject":[],"published":{"date-parts":[[2025,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Balanced ID-OOD tradeoff transfer makes query based detectors good few shot learners","name":"articletitle","label":"Article Title"},{"value":"High-Confidence Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.hcc.2024.100237","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 The Author(s). Published by Elsevier B.V. on behalf of Shandong University.","name":"copyright","label":"Copyright"}],"article-number":"100237"}}