{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:35:34Z","timestamp":1778081734919,"version":"3.51.4"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198175","type":"print"},{"value":"9783031198182","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19818-2_7","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T16:21:10Z","timestamp":1666369270000},"page":"108-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":120,"title":["Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation"],"prefix":"10.1007","author":[{"given":"Sunghwan","family":"Hong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seokju","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisu","family":"Nam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungryong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"7_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Boudiaf, M., Kervadec, H., Masud, Z.I., Piantanida, P., Ben Ayed, I., Dolz, J.: Few-shot segmentation without meta-learning: a good transductive inference is all you need? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01376"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional Nets, Atrous convolution, and fully connected CRFs. IEEE Trans. Patt. Anal. Mach. Intell. (2017)","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Chung, J., Tai, Y.W., Tang, C.K.: CascadePSP: toward class-agnostic and very high-resolution segmentation via global and local refinement. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00891"},{"key":"7_CR6","unstructured":"Cho, S., Hong, S., Jeon, S., Lee, Y., Sohn, K., Kim, S.: CATs: cost aggregation transformers for visual correspondence. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)"},{"key":"7_CR7","unstructured":"Dai, Z., Liu, H., Le, Q., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. Adv. Neural Inf. Process. Syst. 34, 3965\u20133977 (2021)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M., Morcos, A., Biroli, G., Sagun, L.: ConViT: improving vision transformers with soft convolutional inductive biases. arXiv preprint arXiv:2103.10697 (2021)","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"7_CR9","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR10","unstructured":"Dong, N., Xing, E.P.: Few-shot semantic segmentation with prototype learning. In: BMVC (2018)"},{"key":"7_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"7_CR12","doi-asserted-by":"publisher","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. (2010). https:\/\/doi.org\/10.1007\/s11263-009-0275-4","DOI":"10.1007\/s11263-009-0275-4"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.378"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Ham, B., Cho, M., Schmid, C., Ponce, J.: Proposal flow: semantic correspondences from object proposals. IEEE Trans. Patt. Anal. Mach. Intell. (2017)","DOI":"10.1109\/TPAMI.2017.2724510"},{"key":"7_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, S.: Deep matching prior: test-time optimization for dense correspondence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00976"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Hosni, A., Rhemann, C., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. PAMI (2012)","DOI":"10.1109\/CVPR.2011.5995372"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., Lin, S.: Local relation networks for image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3464\u20133473 (2019)","DOI":"10.1109\/ICCV.2019.00356"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Huang, S., Wang, Q., Zhang, S., Yan, S., He, X.: Dynamic context correspondence network for semantic alignment. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00210"},{"key":"7_CR22","doi-asserted-by":"publisher","unstructured":"Jeon, S., Min, D., Kim, S., Choe, J., Sohn, K.: Guided semantic flow. In: ECCV. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_38","DOI":"10.1007\/978-3-030-58604-1_38"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, W., Trulls, E., Hosang, J., Tagliasacchi, A., Yi, K.M.: COTR: correspondence transformer for matching across images. arXiv preprint arXiv:2103.14167 (2021)","DOI":"10.1109\/ICCV48922.2021.00615"},{"key":"7_CR24","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: International Conference on Machine Learning, pp. 5156\u20135165. PMLR (2020)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Kim, S., Min, D., Ham, B., Jeon, S., Lin, S., Sohn, K.: FCSS: fully convolutional self-similarity for dense semantic correspondence. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.73"},{"key":"7_CR26","unstructured":"Lee, J.Y., DeGol, J., Fragoso, V., Sinha, S.N.: Patchmatch-based neighborhood consensus for semantic correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"7_CR27","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNet: learning object-aware semantic correspondence. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sevilla-Lara, L., Sun, D., Kim, J., Kim, J.: Adaptive prototype learning and allocation for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8334\u20138343 (2021)","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Li, S., Han, K., Costain, T.W., Howard-Jenkins, H., Prisacariu, V.: Correspondence networks with adaptive neighbourhood consensus. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01021"},{"key":"7_CR30","doi-asserted-by":"crossref","unstructured":"Li, X., Wei, T., Chen, Y.P., Tai, Y.W., Tang, C.K.: FSS-1000: a 1000-class dataset for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"7_CR31","doi-asserted-by":"publisher","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","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7_CR32","unstructured":"Liu, W., Zhang, C., Ding, H., Hung, T.Y., Lin, G.: Few-shot segmentation with optimal transport matching and message flow. arXiv preprint arXiv:2108.08518 (2021)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhang, C., Lin, G., Liu, F.: CRNet: cross-reference networks for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00422"},{"key":"7_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhu, L., Yamada, M., Yang, Y.: Semantic correspondence as an optimal transport problem. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00452"},{"key":"7_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-58545-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Liu","year":"2020","unstructured":"Liu, Y., Zhang, X., Zhang, S., He, X.: Part-aware prototype network for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 142\u2013158. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_9"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"7_CR38","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Lu, Z., He, S., Zhu, X., Zhang, L., Song, Y.Z., Xiang, T.: Simpler is better: few-shot semantic segmentation with classifier weight transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00862"},{"key":"7_CR40","doi-asserted-by":"crossref","unstructured":"Min, J., Kang, D., Cho, M.: Hypercorrelation squeeze for few-shot segmentation. arXiv preprint arXiv:2104.01538 (2021)","DOI":"10.1109\/ICCV48922.2021.00686"},{"key":"7_CR41","unstructured":"Min, J., Kim, S., Cho, M.: Convolutional hough matching networks for robust and efficient visual correspondence. arXiv preprint arXiv:2109.05221 (2021)"},{"key":"7_CR42","doi-asserted-by":"crossref","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Hyperpixel Flow: semantic correspondence with multi-layer neural features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00349"},{"key":"7_CR43","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: SPair-71k: a large-scale benchmark for semantic correspondence. arXiv preprint arXiv:1908.10543 (2019)"},{"key":"7_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58555-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Min","year":"2020","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Learning to compose hypercolumns for visual correspondence. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 346\u2013363. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_21"},{"key":"7_CR45","doi-asserted-by":"crossref","unstructured":"Nguyen, K., Todorovic, S.: Feature weighting and boosting for few-shot segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 622\u2013631 (2019)","DOI":"10.1109\/ICCV.2019.00071"},{"key":"7_CR46","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.178"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383172"},{"key":"7_CR48","unstructured":"Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning (2016)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"7_CR50","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovi\u0107, R., Sivic, J.: End-to-end weakly-supervised semantic alignment. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00723"},{"key":"7_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/978-3-030-58545-7_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"I Rocco","year":"2020","unstructured":"Rocco, I., Arandjelovi\u0107, R., Sivic, J.: Efficient neighbourhood consensus networks via submanifold sparse convolutions. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12354, pp. 605\u2013621. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58545-7_35"},{"key":"7_CR52","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: Neighbourhood consensus networks. arXiv preprint arXiv:1810.10510 (2018)"},{"key":"7_CR53","doi-asserted-by":"publisher","unstructured":"Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. J. Comput. Vis. (2002). https:\/\/doi.org\/10.1023\/A:1014573219977","DOI":"10.1023\/A:1014573219977"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Shaban, A., Bansal, S., Liu, Z., Essa, I., Boots, B.: One-shot learning for semantic segmentation. arXiv preprint arXiv:1709.03410 (2017)","DOI":"10.5244\/C.31.167"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Siam, M., Oreshkin, B., Jagersand, M.: Adaptive masked proxies for few-shot segmentation. arXiv preprint arXiv:1902.11123 (2019)","DOI":"10.1109\/ICCV.2019.00535"},{"key":"7_CR56","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"7_CR57","unstructured":"Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. arXiv preprint arXiv:1703.05175 (2017)"},{"key":"7_CR58","doi-asserted-by":"crossref","unstructured":"Sun, D., Yang, X., Liu, M.Y., Kautz, J.: PWC-Net: CNNs for optical flow using pyramid, warping, and cost volume. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00931"},{"key":"7_CR59","unstructured":"Sun, G., Liu, Y., Liang, J., Van Gool, L.: Boosting few-shot semantic segmentation with transformers. arXiv preprint arXiv:2108.02266 (2021)"},{"key":"7_CR60","unstructured":"Tao, A., Sapra, K., Catanzaro, B.: Hierarchical multi-scale attention for semantic segmentation. arXiv preprint arXiv:2005.10821 (2020)"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Tetko, I.V., Livingstone, D.J., Luik, A.I.: Neural network studies, 1. comparison of overfitting and overtraining. J. Chem. Inf. Comput. Sci. 35, 826\u2013833 (1995)","DOI":"10.1021\/ci00027a006"},{"key":"7_CR62","unstructured":"Tian, Z., Zhao, H., Shu, M., Yang, Z., Li, R., Jia, J.: Prior guided feature enrichment network for few-shot segmentation. IEEE Trans. Patt. Anal. Mach. Intell. (2020)"},{"key":"7_CR63","unstructured":"Tolstikhin, I.O., et al.: MLP-mixer: an all-MLP architecture for vision. Adv. Neural Inf. Process. Syst. 34, 24261\u201324272 (2021)"},{"key":"7_CR64","doi-asserted-by":"crossref","unstructured":"Truong, P., Danelljan, M., Timofte, R.: GLU-Net: global-local universal network for dense flow and correspondences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6258\u20136268 (2020)","DOI":"10.1109\/CVPR42600.2020.00629"},{"key":"7_CR65","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"7_CR66","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. Adv. Neural Inf. Process. Syst. (2016)"},{"key":"7_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1007\/978-3-030-58601-0_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhang, X., Hu, Y., Yang, Y., Cao, X., Zhen, X.: Few-shot semantic segmentation with democratic attention networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 730\u2013746. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_43"},{"key":"7_CR68","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., Feng, J.: PANet: few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00929"},{"key":"7_CR69","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"7_CR70","unstructured":"Wu, C., Wu, F., Qi, T., Huang, Y., Xie, X.: Fastformer: additive attention can be all you need. arXiv preprint arXiv:2108.09084 (2021)"},{"key":"7_CR71","unstructured":"Wu, S., Wu, T., Lin, F., Tian, S., Guo, G.: Fully transformer networks for semantic image segmentation. arXiv preprint arXiv:2106.04108 (2021)"},{"key":"7_CR72","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. arXiv preprint arXiv:2106.14881 (2021)"},{"key":"7_CR73","doi-asserted-by":"crossref","unstructured":"Xie, G.S., Liu, J., Xiong, H., Shao, L.: Scale-aware graph neural network for few-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5475\u20135484 (2021)","DOI":"10.1109\/CVPR46437.2021.00543"},{"key":"7_CR74","doi-asserted-by":"crossref","unstructured":"Xie, G.S., Xiong, H., Liu, J., Yao, Y., Shao, L.: Few-shot semantic segmentation with cyclic memory network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00720"},{"key":"7_CR75","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Nystr\u00f6mformer: A nystr\u00f6m-based algorithm for approximating self-attention (2021)","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"7_CR76","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1007\/978-3-030-58598-3_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Yang","year":"2020","unstructured":"Yang, B., Liu, C., Li, B., Jiao, J., Ye, Q.: Prototype mixture models for few-shot semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 763\u2013778. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_45"},{"key":"7_CR77","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhuo, W., Qi, L., Shi, Y., Gao, Y.: Mining latent classes for few-shot segmentation. arXiv preprint arXiv:2103.15402 (2021)","DOI":"10.1109\/ICCV48922.2021.00860"},{"key":"7_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiao, J., Qin, T.: Self-guided and cross-guided learning for few-shot segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00821"},{"key":"7_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Guo, J., Wu, Q., Yao, R.: Pyramid graph networks with connection attentions for region-based one-shot semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9587\u20139595 (2019)","DOI":"10.1109\/ICCV.2019.00968"},{"key":"7_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, G., Liu, F., Yao, R., Shen, C.: CANet: class-agnostic segmentation networks with iterative refinement and attentive few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5217\u20135226 (2019)","DOI":"10.1109\/CVPR.2019.00536"},{"key":"7_CR81","unstructured":"Zhang, G., Kang, G., Wei, Y., Yang, Y.: Few-shot segmentation via cycle-consistent transformer. arXiv preprint arXiv:2106.02320 (2021)"},{"key":"7_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, H., Ding, H.: Prototypical matching and open set rejection for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"7_CR83","doi-asserted-by":"crossref","unstructured":"Zhao, D., Song, Z., Ji, Z., Zhao, G., Ge, W., Yu, Y.: Multi-scale matching networks for semantic correspondence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3354\u20133364 (2021)","DOI":"10.1109\/ICCV48922.2021.00334"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19818-2_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T14:19:36Z","timestamp":1710339576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19818-2_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198175","9783031198182"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19818-2_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}