{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:08:15Z","timestamp":1776290895601,"version":"3.50.1"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012601","type":"print"},{"value":"9783030012618","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01261-8_1","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T12:14:51Z","timestamp":1539000891000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2045,"title":["Group Normalization"],"prefix":"10.1007","author":[{"given":"Yuxin","family":"Wu","sequence":"first","affiliation":[]},{"given":"Kaiming","family":"He","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"key":"1_CR1","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7676","key":"1_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: ICLR Workshop (2016)","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1_CR9","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS (2015)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"2","key":"1_CR14","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"David G. Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. In: IJCV (2004)","journal-title":"International Journal of Computer Vision"},{"key":"1_CR15","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. In: IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"1_CR17","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016). arXiv:1607.06450"},{"key":"1_CR18","unstructured":"Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance normalization: the missing ingredient for fast stylization (2016). arXiv:1607.08022"},{"key":"1_CR19","unstructured":"Salimans, T., Kingma, D.P.: Weight normalization: a simple reparameterization to accelerate training of deep neural networks. In: NIPS (2016)"},{"key":"1_CR20","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"1_CR21","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017). arXiv:1705.06950"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533\u2013536 (1986)","journal-title":"Nature"},{"issue":"8","key":"1_CR23","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1_CR24","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NIPS (2014)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"1_CR26","unstructured":"Lyu, S., Simoncelli, E.P.: Nonlinear image representation using divisive normalization. In: CVPR (2008)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Jarrett, K., Kavukcuoglu, K., LeCun, Y., et al.: What is the best multi-stage architecture for object recognition? In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"1_CR28","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: NIPS (2012)"},{"key":"1_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"1_CR30","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"1_CR32","unstructured":"Rebuffi, S.A., Bilen, H., Vedaldi, A.: Learning multiple visual domains with residual adapters. In: NIPS (2017)"},{"key":"1_CR33","unstructured":"Arpit, D., Zhou, Y., Kota, B., Govindaraju, V.: Normalization propagation: a parametric technique for removing internal covariate shift in deep networks. In: ICML (2016)"},{"key":"1_CR34","unstructured":"Ren, M., Liao, R., Urtasun, R., Sinz, F.H., Zemel, R.S.: Normalizing the normalizers: comparing and extending network normalization schemes. In: ICLR (2017)"},{"key":"1_CR35","unstructured":"Ioffe, S.: Batch renormalization: towards reducing minibatch dependence in batch-normalized models. In: NIPS (2017)"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Peng, C., et al.: MegDet: a large mini-batch object detector. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00647"},{"key":"1_CR37","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: NIPS (2012)"},{"key":"1_CR38","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications (2017). arXiv:1704.04861"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. In: IJCV (2001)","DOI":"10.1023\/A:1011139631724"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Jegou, H., Douze, M., Schmid, C., Perez, P.: Aggregating local descriptors into a compact image representation. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383266"},{"key":"1_CR44","unstructured":"Dieleman, S., De Fauw, J., Kavukcuoglu, K.: Exploiting cyclic symmetry in convolutional neural networks. In: ICML (2016)"},{"key":"1_CR45","unstructured":"Cohen, T., Welling, M.: Group equivariant convolutional networks. In: ICML (2016)"},{"issue":"2","key":"1_CR46","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1017\/S0952523800009640","volume":"9","author":"DJ Heeger","year":"1992","unstructured":"Heeger, D.J.: Normalization of cell responses in cat striate cortex. Vis. Neurosci. 9(2), 181\u2013197 (1992)","journal-title":"Vis. Neurosci."},{"issue":"8","key":"1_CR47","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1038\/90526","volume":"4","author":"O Schwartz","year":"2001","unstructured":"Schwartz, O., Simoncelli, E.P.: Natural signal statistics and sensory gain control. Nat. Neurosci. 4(8), 819 (2001)","journal-title":"Nat. Neurosci."},{"issue":"1","key":"1_CR48","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.: Natural image statistics and neural representation. Ann. Rev. Neurosci. 24(1), 1193\u20131216 (2001)","journal-title":"Ann. Rev. Neurosci."},{"issue":"1","key":"1_CR49","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/nrn3136","volume":"13","author":"M Carandini","year":"2012","unstructured":"Carandini, M., Heeger, D.J.: Normalization as a canonical neural computation. Nat. Rev. Neurosci. 13(1), 51 (2012)","journal-title":"Nat. Rev. Neurosci."},{"key":"1_CR50","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"1_CR51","unstructured":"Abadi, M., et al.: Tensorflow: a system for large-scale machine learning. In: Operating Systems Design and Implementation (OSDI) (2016)"},{"key":"1_CR52","unstructured":"Gross, S., Wilber, M.: Training and investigating Residual Nets (2016). https:\/\/github.com\/facebook\/fb.resnet.torch"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"1_CR54","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training ImageNet in 1 hour (2017). arXiv:1706.02677"},{"key":"1_CR55","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks (2014). arXiv:1404.5997"},{"key":"1_CR56","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning (2016). arXiv:1606.04838"},{"key":"1_CR57","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1_CR59","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"issue":"7","key":"1_CR61","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.: Object detection networks on convolutional feature maps. TPAMI 39(7), 1476\u20131481 (2017)","journal-title":"TPAMI"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Li, Z., Peng, C., Yu, G., Zhang, X., Deng, Y., Sun, J.: DetNet: a backbone network for object detection (2018). arXiv:1804.06215","DOI":"10.1007\/978-3-030-01240-3_21"},{"key":"1_CR63","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01261-8_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:58:37Z","timestamp":1775242717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01261-8_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012601","9783030012618"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}