{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:27:28Z","timestamp":1775744848354,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,7,22]],"date-time":"2019-07-22T00:00:00Z","timestamp":1563753600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,22]],"date-time":"2019-07-22T00:00:00Z","timestamp":1563753600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11263-019-01198-w","type":"journal-article","created":{"date-parts":[[2019,7,22]],"date-time":"2019-07-22T12:02:52Z","timestamp":1563796972000},"page":"742-755","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":340,"title":["Group Normalization"],"prefix":"10.1007","volume":"128","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7348-6609","authenticated-orcid":false,"given":"Yuxin","family":"Wu","sequence":"first","affiliation":[]},{"given":"Kaiming","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,22]]},"reference":[{"key":"1198_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et\u00a0al. (2016). Tensorflow: A system for large-scale machine learning. In Operating systems design and implementation (OSDI)."},{"key":"1198_CR2","unstructured":"Arpit, D., Zhou, Y., Kota, B., & Govindaraju, V. (2016). Normalization propagation: A parametric technique for removing internal covariate shift in deep networks. In International conference on machine learning (ICML)."},{"key":"1198_CR3","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. arXiv:1607.06450 ."},{"key":"1198_CR4","unstructured":"Bottou, L., Curtis, F. E., & Nocedal, J. (2016). Optimization methods for large-scale machine learning. arXiv:1606.04838 ."},{"key":"1198_CR5","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/nrn3136","volume":"13","author":"M Carandini","year":"2012","unstructured":"Carandini, M., & Heeger, D. J. (2012). Normalization as a canonical neural computation. Nature Reviews Neuroscience, 13, 51.","journal-title":"Nature Reviews Neuroscience"},{"key":"1198_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., & Zisserman, A. (2017). Quo vadis, action recognition? A new model and the kinetics dataset. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.502"},{"key":"1198_CR7","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.195"},{"key":"1198_CR8","unstructured":"Cohen, T., & Welling, M. (2016). Group equivariant convolutional networks. In International conference on machine learning (ICML)."},{"key":"1198_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2005.177"},{"key":"1198_CR10","unstructured":"Dean, J., Corrado, G., Monga, R., Chen, K., Devin, M., Mao, M., Senior, A., Tucker, P., Yang, K., Le, Q. V., et\u00a0al. (2012). Large scale distributed deep networks. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR11","unstructured":"Dieleman, S., De\u00a0Fauw, J., & Kavukcuoglu, K. (2016). Exploiting cyclic symmetry in convolutional neural networks. In International conference on machine learning (ICML)."},{"key":"1198_CR12","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast R-CNN. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.169"},{"key":"1198_CR13","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., & He, K. (2018). Detectron. https:\/\/github.com\/facebookresearch\/detectron ."},{"key":"1198_CR14","unstructured":"Gitman, Y. Y. I., & Ginsburg, B. (2017). Scaling SGD batch size to 32\u00a0k for imagenet training. arXiv:1708.03888 ."},{"key":"1198_CR15","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In International conference on artificial intelligence and statistics (AISTATS)."},{"key":"1198_CR16","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial nets. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR17","unstructured":"Goyal, P., Doll\u00e1r, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., et al. (2017). Accurate, large minibatch SGD: Training ImageNet in 1\u00a0hour. arXiv:1706.02677 ."},{"key":"1198_CR18","unstructured":"Gross, S., & Wilber, M. (2016). Training and investigating residual nets. https:\/\/github.com\/facebook\/fb.resnet.torch ."},{"key":"1198_CR19","unstructured":"He, K., Girshick, R., & Doll\u00e1r, P. (2018). Rethinking imagenet pre-training. arXiv:1811.08883 ."},{"key":"1198_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask R-CNN. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.322"},{"key":"1198_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.123"},{"key":"1198_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.90"},{"key":"1198_CR23","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1017\/S0952523800009640","volume":"9","author":"DJ Heeger","year":"1992","unstructured":"Heeger, D. J. (1992). Normalization of cell responses in cat striate cortex. Visual Neuroscience, 9, 181\u2013197.","journal-title":"Visual Neuroscience"},{"key":"1198_CR24","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9, 1735\u20131780.","journal-title":"Neural Computation"},{"key":"1198_CR25","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 ."},{"key":"1198_CR26","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van\u00a0der Maaten, L., & Weinberger, K.Q. (2017). Densely connected convolutional networks. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.243"},{"key":"1198_CR27","unstructured":"Ioffe, S. (2017). Batch renormalization: Towards reducing minibatch dependence in batch-normalized models. In Neural Information processing systems (NeurIPS)."},{"key":"1198_CR28","unstructured":"Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (ICML)."},{"key":"1198_CR29","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.632"},{"key":"1198_CR30","doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., LeCun, Y., et al. (2009). What is the best multi-stage architecture for object recognition? In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"1198_CR31","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., Schmid, C., & Perez, P. (2010). Aggregating local descriptors into a compact image representation. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"1198_CR32","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., et al. (2017). The Kinetics human action video dataset. arXiv:1705.06950 ."},{"key":"1198_CR33","unstructured":"Krizhevsky, A. (2014). One weird trick for parallelizing convolutional neural networks. arXiv:1404.5997 ."},{"key":"1198_CR34","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR35","unstructured":"LeCun, Y., Bottou, L., Orr, G. B., & M\u00fcller, K. R. (1998). Efficient backprop. In Neural networks: Tricks of the trade."},{"key":"1198_CR36","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., & Sun, J. (2018). DetNet: A backbone network for object detection. arXiv:1804.06215 ."},{"key":"1198_CR37","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017a). Feature pyramid networks for object detection. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.106"},{"key":"1198_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K., & Doll\u00e1r, P. (2017b). Focal loss for dense object detection. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.324"},{"key":"1198_CR39","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1198_CR40","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1198_CR41","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision (IJCV), 60, 91\u2013110.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1198_CR42","unstructured":"Lyu, S., & Simoncelli, E. P. (2008). Nonlinear image representation using divisive normalization. In Computer vision and pattern recognition (CVPR)."},{"key":"1198_CR43","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1023\/A:1011139631724","volume":"42","author":"A Oliva","year":"2001","unstructured":"Oliva, A., & Torralba, A. (2001). Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision (IJCV), 42, 145\u2013175.","journal-title":"International Journal of Computer Vision (IJCV)"},{"key":"1198_CR44","doi-asserted-by":"crossref","unstructured":"Peng, C., Xiao, T., Li, Z., Jiang, Y., Zhang, X., Jia, K., Yu, G., & Sun, J. (2018). MegDet: A large mini-batch object detector. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00647"},{"key":"1198_CR45","doi-asserted-by":"crossref","unstructured":"Perronnin, F., & Dance, C. (2007). Fisher kernels on visual vocabularies for image categorization. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2007.383266"},{"key":"1198_CR46","unstructured":"Rebuffi, S. A., Bilen, H., & Vedaldi, A. (2017). Learning multiple visual domains with residual adapters. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR47","unstructured":"Ren, M., Liao, R., Urtasun, R., Sinz, F. H., & Zemel, R. S. (2017a). Normalizing the normalizers: Comparing and extending network normalization schemes. In International conference on learning representations (ICLR)."},{"key":"1198_CR48","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR49","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1109\/TPAMI.2016.2601099","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Zhang, X., & Sun, J. (2017b). Object detection networks on convolutional feature maps. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 39, 1476\u20131481.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)"},{"key":"1198_CR50","first-page":"1","volume":"5","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 5, 1.","journal-title":"Nature"},{"key":"1198_CR51","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision (IJCV)., 115, 211\u2013252.","journal-title":"International Journal of Computer Vision (IJCV)."},{"key":"1198_CR52","unstructured":"Salimans, T., & Kingma, D. P. (2016). Weight normalization: A simple reparameterization to accelerate training of deep neural networks. In Neural information processing systems (NeurIPS)."},{"key":"1198_CR53","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1038\/90526","volume":"4","author":"O Schwartz","year":"2001","unstructured":"Schwartz, O., & Simoncelli, E. P. (2001). Natural signal statistics and sensory gain control. Nature Neuroscience, 4, 819.","journal-title":"Nature Neuroscience"},{"key":"1198_CR54","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2014). Overfeat: Integrated recognition, localization and detection using convolutional networks. In International conference on learning representations (ICLR)."},{"key":"1198_CR55","unstructured":"Shillingford, B., Assael, Y., Hoffman, M. W., Paine, T., Hughes, C., Prabhu, U., et al. (2018). Large-scale visual speech recognition. arXiv:1807.05162 ."},{"key":"1198_CR56","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., Guez, A., et al. (2017). Mastering the game of go without human knowledge. Nature, 550, 354.","journal-title":"Nature"},{"key":"1198_CR57","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1146\/annurev.neuro.24.1.1193","volume":"24","author":"EP Simoncelli","year":"2001","unstructured":"Simoncelli, E. P., & Olshausen, B. A. (2001). Natural image statistics and neural representation. Annual Review of Neuroscience, 24, 1193\u20131216.","journal-title":"Annual Review of Neuroscience"},{"key":"1198_CR58","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International conference on learning representations (ICLR)."},{"key":"1198_CR59","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., & Vanhoucke, V. (2016a). Inception-v4, inception-resnet and the impact of residual connections on learning. In ICLR workshop.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1198_CR60","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1198_CR61","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016b). Rethinking the inception architecture for computer vision. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2016.308"},{"key":"1198_CR62","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3D convolutional networks. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2015.510"},{"key":"1198_CR63","unstructured":"Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2016). Instance normalization: The missing ingredient for fast stylization. arXiv:1607.08022 ."},{"key":"1198_CR64","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., & He, K. (2018). Non-local neural networks. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1198_CR65","doi-asserted-by":"crossref","unstructured":"Wu, Y., & He, K. (2018). Group normalization. In European conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"1198_CR66","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., & He, K. (2017). Aggregated residual transformations for deep neural networks. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.634"},{"key":"1198_CR67","unstructured":"Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional neural networks. In European conference on computer vision (ECCV)."},{"key":"1198_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018). ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In Computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00716"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01198-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-019-01198-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-019-01198-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T09:59:31Z","timestamp":1664013571000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-019-01198-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,22]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["1198"],"URL":"https:\/\/doi.org\/10.1007\/s11263-019-01198-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,22]]},"assertion":[{"value":"1 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}