{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:04:26Z","timestamp":1766138666692,"version":"3.28.0"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,20]],"date-time":"2024-04-20T00:00:00Z","timestamp":1713571200000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1007\/s00530-024-01330-y","type":"journal-article","created":{"date-parts":[[2024,4,21]],"date-time":"2024-04-21T02:59:43Z","timestamp":1713668383000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PathNet: a novel multi-pathway convolutional neural network for few-shot image classification from scratch"],"prefix":"10.1007","volume":"30","author":[{"given":"Zhonghua","family":"Fan","sequence":"first","affiliation":[]},{"given":"Dongbai","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Hongying","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,20]]},"reference":[{"key":"1330_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"1330_CR2","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"1330_CR3","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR) (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"1330_CR4","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, W., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1330_CR5","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"1330_CR6","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1330_CR7","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1330_CR8","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1330_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"1330_CR10","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1330_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1330_CR12","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697\u20138710 (2018)","DOI":"10.1109\/CVPR.2018.00907"},{"key":"1330_CR13","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1330_CR14","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)"},{"key":"1330_CR15","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1330_CR16","doi-asserted-by":"publisher","unstructured":"Howard, A., et al.: Searching for MobileNetV3. 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 1314\u20131324 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1330_CR17","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1330_CR18","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, D.J.: Shufflenet V2: Practical guidelines for efficient cnn architecture design. In Eur. Conf. Comput. Vis. (ECCV), volume 11218 of Lecture Notes in Computer Science, pp. 122\u2013138. Springer (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"1330_CR19","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"1330_CR20","unstructured":"Tan, M., Le, Q.: Efficientnetv2: Smaller models and faster training. In International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)."},{"key":"1330_CR21","unstructured":"Trockman, A., Zico Kolter, J.: Patches are all you need? arXiv preprint arXiv:2201.09792 (2022)"},{"key":"1330_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the2020s. arXiv preprint arXiv:2201.03545 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1330_CR23","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems, 30 (2017)"},{"key":"1330_CR24","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"1330_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1330_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al.: Swin transformer V2: Scaling up capacity and resolution. arXiv:2111.09883 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1330_CR27","unstructured":"Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., Lucic, M., Dosovitskiy, A.: Mlp-mixer: An all-mlp architecture for vision. arXiv preprint arXiv:2105.01601 (2021)"},{"key":"1330_CR28","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Computation. (1989)","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"1330_CR29","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In European Conference on Computer Vision, pp. 630\u2013645. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"1330_CR30","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In European Conference on Computer Vision, pp. 646\u2013661. Springer (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"1330_CR31","doi-asserted-by":"publisher","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVGG: Making VGG-style ConvNets great again. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, pp. 13728\u201313737 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01352","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"1330_CR32","unstructured":"Bello, I., Fedus, W., Du, X., Cubuk, E.D., Srinivas, A., Lin, T.-Y., Shlens, J., Zoph, B.: Revisiting resnets: Improved training and scaling strategies. In Advances in Neural Information Processing Systems (2021)"},{"key":"1330_CR33","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization. arXiv:2102.06171 (2021)"},{"key":"1330_CR34","unstructured":"Zhang, H., Wu, C., Zhang, Z., Zhu, Y., Zhang, Z., Lin, H., Sun, Y., He, H., Mueller, J., Manmatha, R., et al. Resnest: Split-attention networks. arXiv:2004.08955 (2020)"},{"key":"1330_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1330_CR36","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention augmented convolutional networks. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3286\u20133295 (2019)","DOI":"10.1109\/ICCV.2019.00338"},{"key":"1330_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, H,, Zu, K., Lu, J., et al.: EPSANet: An efficient pyramid squeeze attention block on convolutional neural network. In Proceedings of the Asian Conference on Computer Vision, pp. 1161\u20131177 (2022)","DOI":"10.1007\/978-3-031-26313-2_33"},{"key":"1330_CR38","unstructured":"Urban, G., Geras, K.J., Kahou, S.E., Aslan, O., Wang, S., Caruana, R., Mohamed, A., Philipose, M., Richardson, M.: Do deep convolutional nets really need to be deep and convolutional? arXiv preprint arXiv:1603.05691 (2016)"},{"key":"1330_CR39","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"1330_CR40","doi-asserted-by":"crossref","unstructured":"Du, X., Lin, T.Y., Jin, P., Ghiasi, G., Tan, M., Cui, Y., Le, Q.V., Song, X.: Spinenet: Learning scale-permuted backbone for recognition and localization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11592\u201311601 (2020)","DOI":"10.1109\/CVPR42600.2020.01161"},{"key":"1330_CR41","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Johnson, J., Xie, S., Lo, W.-Y., Doll\u00e1r, P.: On network design spaces for visual recognition. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1882\u20131890 (2019)","DOI":"10.1109\/ICCV.2019.00197"},{"key":"1330_CR42","unstructured":"Touvron, H., Bojanowski, P., Caron, M., Cord, M., El-Nouby, A., Grave, E., Izacard, G., Joulin, A., Synnaeve, G., Verbeek, J., J\u00e9gou, H.: Resmlp: Feedforward networks for image classification with data-efficient training. arXiv preprint arXiv:2105.03404 (2021)"},{"key":"1330_CR43","first-page":"9204","volume":"34","author":"H Liu","year":"2021","unstructured":"Liu, H., Dai, Z., So, D.R., Le, Q.V.: Pay attention to mlps. Adv. Neural. Inf. Process. Syst. 34, 9204\u20139215 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1330_CR44","unstructured":"Chen, S., Xie, E., Ge, C., Chen, R., Liang, D., Luo, P.: CycleMLP: A MLP-like Architecture for Dense Prediction. arXiv:2107.10224 (2022)"},{"key":"1330_CR45","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers and distillation through attention. In International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"1330_CR46","doi-asserted-by":"crossref","unstructured":"Heo B, et al.: Rethinking spatial dimensions of vision transformers. arXiv preprint arXiv:2103.16302 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"1330_CR47","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Tay, F.E.H., Feng, J., Yan, S.: Tokens to-token vit: Training vision transformers from scratch on imagenet. In Proceedings of IEEE Int. Conf. on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1330_CR48","unstructured":"Han, K., Xiao, A., Wu. E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. arXiv:2103.00112 (2021)"},{"key":"1330_CR49","doi-asserted-by":"crossref","unstructured":"Chen, C.-F., Fan, Q., Panda, R.: Crossvit: Cross-attention multi-scale vision transformer for image classification. arXiv:2103.14899 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"1330_CR50","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: Coatnet: Marrying convolution and attention for all data sizes. Adv. Neural. Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1330_CR51","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: Introducing convolutions to vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"issue":"11","key":"1330_CR52","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"1330_CR53","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv:1607.06450 (2016)"},{"key":"1330_CR54","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv:1606.08415 (2016)."},{"key":"1330_CR55","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th International Conference on International Conference on Machine Learning, pp. 807\u2013814 (2010)"},{"key":"1330_CR56","unstructured":"Liu, Y.C., Shao, Z.R., Hoffmann, N.: Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv:2112.05561 (2021)"},{"key":"1330_CR57","doi-asserted-by":"crossref","unstructured":"Nilsback, M.-E., Zisserman, A.: Automated flower classification over a large number of classes. In 2008 Sixth Indian Conference on Computer Vision, Graphics & Image Processing, pp. 722\u2013729 (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"1330_CR58","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In International Conference on Learning Representations (2019)"},{"key":"1330_CR59","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Master\u2019s thesis, Department of Computer Science, University of Toronto (2009)"},{"key":"1330_CR60","unstructured":"Le, Y., Yang, X.: Tiny imagenet visual recognition challenge. CS 231N (2015)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01330-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01330-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01330-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T18:37:49Z","timestamp":1731782269000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01330-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,20]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1330"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01330-y","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2024,4,20]]},"assertion":[{"value":"26 December 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"127"}}