{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T21:17:17Z","timestamp":1784063837473,"version":"3.55.0"},"publisher-location":"Cham","reference-count":83,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726453","type":"print"},{"value":"9783031726460","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"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\/978-3-031-72646-0_23","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:45:29Z","timestamp":1730105129000},"page":"395-415","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["DenseNets Reloaded: Paradigm Shift Beyond ResNets and\u00a0ViTs"],"prefix":"10.1007","author":[{"given":"Donghyun","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeongho","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyoon","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"23_CR1","unstructured":"Github repository: Swin transformer for object detection. https:\/\/github.com\/SwinTransformer\/Swin-Transformer-Object-Detection"},{"key":"23_CR2","unstructured":"Ba, J., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"23_CR3","first-page":"22614","volume":"34","author":"I Bello","year":"2021","unstructured":"Bello, I., et al.: Revisiting ResNets: improved training and scaling strategies. Conf. Neural Inf. Process. Syst. (NeurIPS) 34, 22614\u201322627 (2021)","journal-title":"Conf. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"23_CR4","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization. In: International Conference on Machine Learning (ICML), pp. 1059\u20131071 (2021)"},{"key":"23_CR5","unstructured":"Cai, Y., et al.: Reversible column networks. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"23_CR7","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., Feng, J.: Dual path networks. In: Conference on Neural Information Processing Systems (NIPS), vol. 30 (2017)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132829 (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: IEEE Transactions on Computer Vision and Pattern Recognition Workshop (CVPRW), pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"23_CR10","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. In: Conference on Neural Information Processing Systems (NeurIPS), pp. 3965\u20133977 (2021)"},{"key":"23_CR11","unstructured":"Desai, K., Kaul, G., Aysola, Z., Johnson, J.: RedCaps: Web-curated image-text data created by the people, for the people. arXiv preprint arXiv:2111.11431 (2021)"},{"key":"23_CR12","unstructured":"DeVries, T., Taylor, G.W.: Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552 (2017)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Zhou, Y., Han, J., Ding, G., Sun, J.: Scaling up your kernels to 31x31: revisiting large kernel design in CNNs. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01166"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"23_CR15","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"23_CR16","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: Training ImageNet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Guo, M.H., Lu, C.Z., Liu, Z.N., Cheng, M.M., Hu, S.M.: Visual attention network. Computational Visual Media (CVMJ) (2023)","DOI":"10.1007\/s41095-023-0364-2"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., Kim, J.: Deep pyramidal residual networks. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 5927\u20135935 (2017)","DOI":"10.1109\/CVPR.2017.668"},{"key":"23_CR19","unstructured":"Han, D., Yoo, Y., Kim, B., Heo, B.: Learning features with parameter-free layers. arXiv preprint arXiv:2202.02777 (2022)"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Han, D., Yun, S., Heo, B., Yoo, Y.: Rethinking channel dimensions for efficient model design. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 732\u2013741 (2021)","DOI":"10.1109\/CVPR46437.2021.00079"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., Shi, H.: Neighborhood attention transformer. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 6185\u20136194 (2023)","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"23_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"23_CR25","unstructured":"Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Pleiss, G., Maaten, L.v.d., Weinberger, K.Q.: Convolutional networks with dense connectivity. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 44(12), 8704\u20138716 (2022)","DOI":"10.1109\/TPAMI.2019.2918284"},{"key":"23_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"23_CR28","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (ICML), pp. 448\u2013456. PMLR (2015)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"J\u00e9gou, S., Drozdzal, M., Vazquez, D., Romero, A., Bengio, Y.: The one hundred layers tiramisu: Fully convolutional DenseNets for semantic segmentation. In: IEEE Transactions on Computer Vision and Pattern Recognition Workshop (CVPRW), pp. 11\u201319 (2017)","DOI":"10.1109\/CVPRW.2017.156"},{"key":"23_CR30","unstructured":"Kornblith, S., Norouzi, M., Lee, H., Hinton, G.: Similarity of neural network representations revisited. In: International Conference on Machine Learning (ICML), pp. 3519\u20133529 (2019)"},{"key":"23_CR31","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2012)","journal-title":"Commun. ACM"},{"key":"23_CR32","unstructured":"Le, Y., Yang, X.S.: Tiny ImageNet visual recognition challenge (2015). https:\/\/api.semanticscholar.org\/CorpusID:16664790"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Lee, Y., Hwang, J.w., Lee, S., Bae, Y., Park, J.: An energy and GPU-computation efficient backbone network for real-time object detection. In: IEEE Transactions on Computer Vision and Pattern Recognition Workshop (CVPRW), pp. 752\u2013760 (2019)","DOI":"10.1109\/CVPRW.2019.00103"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: CenterMask: real-time anchor-free instance segmentation. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"23_CR35","unstructured":"Li, S., et al.: MogaNet: multi-order gated aggregation network. In: International Conference on Learning Representations (ICLR) (2024). https:\/\/openreview.net\/forum?id=XhYWgjqCrV"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MicroNet: improving image recognition with extremely low flops. In: International Conference on Computer Vision (ICCV), pp. 468\u2013477 (2021)","DOI":"10.1109\/ICCV48922.2021.00052"},{"key":"23_CR37","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":"23_CR38","doi-asserted-by":"crossref","unstructured":"Lin, W., Wu, Z., Chen, J., Huang, J., Jin, L.: Scale-aware modulation meet transformer. In: International Conference on Computer Vision (ICCV), pp. 5992\u20136003 (10 2023)","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"23_CR39","unstructured":"Liu, S., et al.: More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"23_CR42","unstructured":"Loshchilov, I., Hutter, F.: SGDR: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"23_CR43","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Parihar, A.S., Java, A.: Densely connected convolutional transformer for single image dehazing. J. Visual Commun. Image Represent. 90, 103722 (2023)","DOI":"10.1016\/j.jvcir.2022.103722"},{"key":"23_CR45","unstructured":"Pleiss, G., Chen, D., Huang, G., Li, T., van\u00a0der Maaten, L., Weinberger, K.Q.: Memory-efficient implementation of DenseNets. arXiv preprint arXiv:1707.06990 (2017)"},{"key":"23_CR46","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., Doll\u00e1r, P.: Designing network design spaces. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 10425\u201310433 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"23_CR48","unstructured":"Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S.N., Lu, J.: HorNet: efficient high-order spatial interactions with recursive gated convolutions. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"issue":"3","key":"23_CR49","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A.G., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"23_CR51","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"23_CR52","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"23_CR53","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT? Data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp.\u00a01\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"23_CR56","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (ICML), pp. 6105\u20136114. PMLR (2019)"},{"key":"23_CR57","unstructured":"Tan, M., Le, Q.V.: EfficientNetV2: smaller models and faster training. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"23_CR58","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning (ICML), pp. 10347\u201310357 (2021)"},{"key":"23_CR59","unstructured":"Touvron, H., et al.: Augmenting convolutional networks with attention-based aggregation. arXiv preprint arXiv:2112.13692 (2021)"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., J\u2019egou, H.: DeiT III: revenge of the ViT. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"23_CR61","unstructured":"Trockman, A., Kolter, J.Z.: Patches are all you need? arXiv preprint arXiv:2201.09792 (2022)"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"23_CR63","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"23_CR64","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.y., Wu, Y.H., Chen, P.Y., Hsieh, J.W., Yeh, I.H.: CSPNet: a new backbone that can enhance learning capability of CNN. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 1571\u20131580 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Wang, L., Cao, M., Yuan, X.: EfficientSCI: densely connected network with space-time factorization for large-scale video snapshot compressive imaging. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 18477\u201318486 (2023)","DOI":"10.1109\/CVPR52729.2023.01772"},{"key":"23_CR66","unstructured":"Wang, R.J., Li, X., Ling, C.X.: Pelee: a real-time object detection system on mobile devices. In: Conference on Neural Information Processing Systems (NeurIPS), pp. 1967\u20131976 (2018)"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: International Conference on Computer Vision (ICCV), pp. 548\u2013558 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Vis. Media (CVMJ) 8(3), 1\u201310 (2022)","DOI":"10.1007\/s41095-022-0274-8"},{"key":"23_CR69","doi-asserted-by":"publisher","first-page":"56416","DOI":"10.1109\/ACCESS.2021.3072211","volume":"9","author":"Z Wang","year":"2021","unstructured":"Wang, Z., Xie, K., Zhang, X.Y., Chen, H.Q., Wen, C., He, J.: Small-object detection based on yolo and dense block via image super-resolution. IEEE Access 9, 56416\u201356429 (2021)","journal-title":"IEEE Access"},{"key":"23_CR70","unstructured":"Wightman, R., Touvron, H., J\u00e9gou, H.: ResNet strikes back: An improved training procedure in timm. https:\/\/github.com\/huggingface\/pytorch-image-models (2021)"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Wu, K., et al.: TinyViT: fast pretraining distillation for small vision transformers. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"23_CR72","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"23_CR73","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"23_CR74","unstructured":"Yang, J., Li, C., Dai, X., Gao, J.: Focal modulation networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"23_CR75","unstructured":"Yang, J., et al.: Focal self-attention for local-global interactions in vision transformers. In: Conference on Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"23_CR76","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: MetaFormer is actually what you need for vision. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR), pp. 10819\u201310829 (2022)","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"23_CR77","doi-asserted-by":"crossref","unstructured":"Yu, W., Zhou, P., Yan, S., Wang, X.: InceptionNext: When inception meets convnext. arXiv preprint arXiv:2303.16900 (2023)","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"23_CR78","doi-asserted-by":"crossref","unstructured":"Yun, S., et al.: CutMix: regularization strategy to train strong classifiers with localizable features. In: International Conference on Computer Vision (ICCV), pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"23_CR79","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"23_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, J., Jin, Y., Xu, J., Xu, X., Zhang, Y.: MDU-Net: multi-scale densely connected u-net for biomedical image segmentation. Health Inf. Sci. Syst. (HISS) 11(1), 13 (2023)","DOI":"10.1007\/s13755-022-00204-9"},{"key":"23_CR81","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"23_CR82","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vis. (IJCV) 127, 302\u2013321 (2018)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"23_CR83","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.: BiFormer: vision transformer with bi-level routing attention. In: IEEE Transactions on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00995"}],"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\/978-3-031-72646-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:57:15Z","timestamp":1730105835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72646-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"ISBN":["9783031726453","9783031726460"],"references-count":83,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72646-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"28 October 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"}}]}}