{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T13:53:28Z","timestamp":1769694808666,"version":"3.49.0"},"reference-count":31,"publisher":"Cambridge University Press (CUP)","issue":"6","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Robotica"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The goal of few-shot semantic segmentation is to learn a segmentation model that can segment novel classes in queries when only a few annotated support examples are available. Due to large intra-class variations, the building of accurate semantic correlation remains a challenging job. Current methods typically use 4D kernels to learn the semantic correlation of feature maps. However, they still face the challenge of reducing the consumption of computation and memory while keeping the availability of correlations mined by their methods. In this paper, we propose the adaptively mining correlation network (AMCNet) to alleviate the aforementioned issues. The key points of AMCNet are the proposed adaptive separable 4D kernel and the learnable pyramid correlation module, which form the basic block for correlation encoder and provide a learnable concatenation operation over pyramid correlation tensors, respectively. Experiments on the PASCAL VOC 2012 dataset show that our AMCNet surpasses the state-of-the-art method by <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S0263574723000206_inline1.png\"\/><jats:tex-math>\n$0.7\\%$\n<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula> and <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"png\" xlink:href=\"S0263574723000206_inline2.png\"\/><jats:tex-math>\n$2.2\\%$\n<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula> on 1-shot and 5-shot segmentation scenarios, respectively.<\/jats:p>","DOI":"10.1017\/s0263574723000206","type":"journal-article","created":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T09:46:00Z","timestamp":1678700760000},"page":"1828-1836","source":"Crossref","is-referenced-by-count":4,"title":["A few-shot semantic segmentation method based on adaptively mining correlation network"],"prefix":"10.1017","volume":"41","author":[{"given":"Zhifu","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4592-3322","authenticated-orcid":false,"given":"Bin","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4191-5974","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"key":"S0263574723000206_ref12","unstructured":"[12] Rocco, I. , Cimpoi, M. , Arandjelovi\u0107, R. , Torii, A. , Pajdla, T. and Sivic, J. , \u201cNeighbourhood consensus networks,\u201d In: Proceedings of the Advances in Neural Information Processing Systems, (2018) pp. 1651\u20131662."},{"key":"S0263574723000206_ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2992433"},{"key":"S0263574723000206_ref10","doi-asserted-by":"crossref","unstructured":"[10] Li, S. , Han, K. , Costain, T. W. , Howard-Jenkins, H. and Prisacariu, V. , \u201cCorrespondence networks with adaptive neighbourhood consensus,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2020) pp. 10193\u201310202.","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"S0263574723000206_ref29","doi-asserted-by":"crossref","unstructured":"[29] Liu, Y. , Zhang, X. , Zhang, S. and He, X. , \u201cPart-aware prototype network for few-shot semantic segmentation,\u201d In: Proceedings of the European Conference on Computer Vision, (2020) pp. 142\u2013158.","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"S0263574723000206_ref1","unstructured":"[1] Simonyan, K. and Zisserman, A. , \u201cVery deep convolutional networks for large-scale image recognition\u201d (2014), arXiv: 1409.1556."},{"key":"S0263574723000206_ref15","unstructured":"[15] Vinyals, O. , Blundell, C. , Lillicrap, T. , Kavukcuoglu, K. and Wierstra, D. , \u201cMatching networks for one shot learning,\u201d In: Proceedings of the Advances in Neural Information Processing Systems, (2016) pp. 3630\u20133638."},{"key":"S0263574723000206_ref8","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721001521"},{"key":"S0263574723000206_ref3","doi-asserted-by":"crossref","unstructured":"[3] Wang, Q. , Zhang, L. , Bertinetto, L. , Hu, W. and Torr, P. H. S. , \u201cFast online object tracking and segmentation: A unifying approach,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2019) pp. 1328\u20131338.","DOI":"10.1109\/CVPR.2019.00142"},{"key":"S0263574723000206_ref13","doi-asserted-by":"crossref","unstructured":"[13] Shaban, A. , Bansal, S. , Liu, Z. , Essa, I. and Bootstitle, B. , \u201cOne-shot learning for semantic segmentation,\u201d (2017), arXiv: 1709.03410.","DOI":"10.5244\/C.31.167"},{"key":"S0263574723000206_ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"S0263574723000206_ref26","doi-asserted-by":"crossref","unstructured":"[26] Xie, G.-S. , Xiong, H. , Liu, J. , Yao, Y. and Shao, L. , \u201cFew-shot semantic segmentation with cyclic memory network,\u201d In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (2021) pp. 7293\u20137302.","DOI":"10.1109\/ICCV48922.2021.00720"},{"key":"S0263574723000206_ref5","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574722000649"},{"key":"S0263574723000206_ref21","doi-asserted-by":"crossref","unstructured":"[21] Wang, K. , Liew, J. H. , Zou, Y. , Zhou, D. and Feng, J. , \u201cPANet: Few-shot image semantic segmentation with prototype alignment,\u201d In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (2019) pp. 622\u2013631.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"S0263574723000206_ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"S0263574723000206_ref19","doi-asserted-by":"crossref","unstructured":"[19] Zhang, C. , Lin, G. , Liu, F. , Yao, R. and Shen, C. , \u201cCANet: Class-agnostic segmentation networks with iterative refinement and attentive few-shot learning,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2019) pp. 5217\u20135226.","DOI":"10.1109\/CVPR.2019.00536"},{"key":"S0263574723000206_ref24","unstructured":"[24] Rakelly, K. , Shelhamer, E. , Darrell, T. , Efros, A. and Levine, S. , \u201cConditional networks for few-shot semantic segmentation,\u201d In: Proceedings of the International Conference on Learning Representations Workshop, (2018)."},{"key":"S0263574723000206_ref20","doi-asserted-by":"crossref","unstructured":"[20] Zhang, C. , Lin, G. , Liu, F. , Guo, J. , Wu, Q. and Yao, R. , \u201cPyramid graph networks with connection attentions for region-based one-shot semantic segmentation,\u201d In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (2019) pp. 9587\u20139595.","DOI":"10.1109\/ICCV.2019.00968"},{"key":"S0263574723000206_ref2","doi-asserted-by":"crossref","unstructured":"[2] Huang, G. , Liu, Z. , van der Maaten, L. and Weinberger, K. Q. , \u201cDensely connected convolutional networks,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2017) pp. 4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"S0263574723000206_ref16","unstructured":"[16] Yang, G. and Ramanan, D. , \u201cVolumetric correspondence networks for optical flow,\u201d In: Proceedings of the Advances in Neural Information Processing Systems, (2019) pp. 794\u2013805."},{"key":"S0263574723000206_ref11","unstructured":"[11] Choy, C. B. , Gwak, J. Y. , Savarese, S. and Chandraker, M. , \u201cUniversal correspondence network,\u201d In: Proceedings of the International Conference on Neural Information Processing Systems, (2016) pp. 2414\u20132422."},{"key":"S0263574723000206_ref31","doi-asserted-by":"crossref","unstructured":"[31] Nguyen, K. and Todorovic, S. , \u201cFeature weighting and boosting for few-shot segmentation,\u201d In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, (2019) pp. 622\u2013631.","DOI":"10.1109\/ICCV.2019.00071"},{"key":"S0263574723000206_ref28","doi-asserted-by":"crossref","unstructured":"[28] Lin, T.-Y. , Maire, M. , Belongie, S. , Hays, J. , Perona, P. , Ramanan, D. , Doll\u00e1r, P. and Zitnick, C. L. , \u201cMicrosoft COCO: common objects in context,\u201d In: Proceedings of the European Conference on Computer Vision, (2014) pp. 740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"S0263574723000206_ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"S0263574723000206_ref25","doi-asserted-by":"crossref","unstructured":"[25] Xie, G.-S. , Liu, J. , Xiong, H. and Shao, L. , \u201cScale-aware graph neural network for few-shot semantic segmentation,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021) pp. 5475\u20135484.","DOI":"10.1109\/CVPR46437.2021.00543"},{"key":"S0263574723000206_ref9","doi-asserted-by":"crossref","unstructured":"[9] Deng, J. , Dong, W. , Socher, R. , Li, L.-J. , Li, K. and Li, F.-F. , \u201cImagenet: A large-scale hierarchical image database,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2009) pp. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"S0263574723000206_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"S0263574723000206_ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01198-w"},{"key":"S0263574723000206_ref30","doi-asserted-by":"crossref","unstructured":"[30] Yang, B. , Liu, C. , Li, B. , Jiao, J. and Ye, Q. , \u201cPrototype mixture models for few-shot semantic segmentation,\u201d In: Proceedings of the European Conference on Computer Vision, (2020) pp. 763\u2013778.","DOI":"10.1007\/978-3-030-58598-3_45"},{"key":"S0263574723000206_ref23","doi-asserted-by":"crossref","unstructured":"[23] Boudiaf, M. , Kervadec, H. , Masud, Z. I. , Piantanida, P. , Ayed, I. B. and Dolz, J. , \u201cFew-shot segmentation without meta-learning: A good transductive inference is all you need?,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021) pp. 13979\u201313988.","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"S0263574723000206_ref22","doi-asserted-by":"crossref","unstructured":"[22] Li, G. , Jampani, V. , Sevilla-Lara, L. , Sun, D. , Kim, J. and Kim, J. , \u201cAdaptive prototype learning and allocation for few-shot segmentation,\u201d In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2021) pp. 8334\u20138343.","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"S0263574723000206_ref4","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574721001053"}],"container-title":["Robotica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0263574723000206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T09:02:11Z","timestamp":1683795731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0263574723000206\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["S0263574723000206"],"URL":"https:\/\/doi.org\/10.1017\/s0263574723000206","relation":{},"ISSN":["0263-5747","1469-8668"],"issn-type":[{"value":"0263-5747","type":"print"},{"value":"1469-8668","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]}}}