{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:57:49Z","timestamp":1775066269919,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319464923","type":"print"},{"value":"9783319464930","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-46493-0_39","type":"book-chapter","created":{"date-parts":[[2016,9,16]],"date-time":"2016-09-16T14:59:53Z","timestamp":1474037993000},"page":"646-661","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1038,"title":["Deep Networks with Stochastic Depth"],"prefix":"10.1007","author":[{"given":"Gao","family":"Huang","sequence":"first","affiliation":[]},{"given":"Yu","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Sedra","sequence":"additional","affiliation":[]},{"given":"Kilian Q.","family":"Weinberger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,9,17]]},"reference":[{"key":"39_CR1","unstructured":"Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)"},{"key":"39_CR2","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009, CVPR 2009. IEEE, pp. 248\u2013255 (2009)"},{"key":"39_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"39_CR4","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229 (2013)"},{"key":"39_CR5","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"39_CR6","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. arXiv preprint arXiv:1412.6806 (2014)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., 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":"39_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. arXiv preprint arXiv:1512.03385 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"39_CR9","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/BF01272517","volume":"1","author":"J H\u00e5stad","year":"1991","unstructured":"H\u00e5stad, J., Goldmann, M.: On the power of small-depth threshold circuits. Comput. Complex. 1(2), 113\u2013129 (1991)","journal-title":"Comput. Complex."},{"key":"39_CR10","volume-title":"Computational Limitations of Small-Depth Circuits","author":"J H\u00e5stad","year":"1987","unstructured":"H\u00e5stad, J.: Computational Limitations of Small-Depth Circuits. MIT Press, Cambridge (1987)"},{"issue":"2","key":"39_CR11","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Networks 5(2), 157\u2013166 (1994)","journal-title":"IEEE Trans. Neural Networks"},{"key":"39_CR12","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"39_CR13","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. arXiv preprint arXiv:1409.5185 (2014)"},{"key":"39_CR14","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"39_CR15","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. arXiv preprint arXiv:1505.00387 (2015)"},{"issue":"1","key":"39_CR16","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"39_CR17","volume-title":"The Cascade-Correlation Learning Architecture","author":"SE Fahlman","year":"1989","unstructured":"Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. Morgan Kaufmann Publishers Inc., San Francisco (1989)"},{"key":"39_CR18","first-page":"625","volume":"11","author":"D Erhan","year":"2010","unstructured":"Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P., Bengio, S.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 11, 625\u2013660 (2010)","journal-title":"J. Mach. Learn. Res."},{"key":"39_CR19","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807\u2013814 (2010)"},{"key":"39_CR20","unstructured":"Wan, L., Zeiler, M., Zhang, S., Cun, Y.L., Fergus, R.: Regularization of neural networks using dropconnect. In: Dasgupta, S., Mcallester, D. (eds.): Proceedings of the 30th International Conference on Machine Learning (ICML-13), JMLR Workshop and Conference Proceedings, vol. 28, pp. 1058\u20131066, May 2013"},{"key":"39_CR21","unstructured":"Goodfellow, I.J., Warde-Farley, D., Mirza, M., Courville, A., Bengio, Y.: Maxout networks. arXiv preprint arXiv:1302.4389 (2013)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Hand, E.M., Doster, T.: Gradual dropin of layers to train very deep neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.515"},{"key":"39_CR23","unstructured":"Zagoruyko, S.: 92.45% on cifar-10 in torch (2015)"},{"key":"39_CR24","unstructured":"Lin, M., Chen, Q., Yan, S.: Network in network. arXiv preprint arXiv:1312.4400 (2013)"},{"key":"39_CR25","unstructured":"Graham, B.: Fractional max-pooling. arXiv preprint arXiv:1412.6071 (2014)"},{"key":"39_CR26","unstructured":"Agostinelli, F., Hoffman, M., Sadowski, P., Baldi, P.: Learning activation functions to improve deep neural networks. arXiv preprint arXiv:1412.6830 (2014)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Liang, M., Hu, X.: Recurrent convolutional neural network for object recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3367\u20133375 (2015)","DOI":"10.1109\/CVPR.2015.7298958"},{"key":"39_CR28","unstructured":"Snoek, J., Rippel, O., Swersky, K., Kiros, R., Satish, N., Sundaram, N., Patwary, M., Ali, M., Adams, R.P., et al.: Scalable bayesian optimization using deep neural networks. arXiv preprint arXiv:1502.05700 (2015)"},{"key":"39_CR29","unstructured":"Srivastava, R.K., Greff, K., Schmidhuber, J.: Training very deep networks. In: Advances in Neural Information Processing Systems, pp. 2368\u20132376 (2015)"},{"key":"39_CR30","unstructured":"Lee, C.Y., Gallagher, P.W., Tu, Z.: Generalizing pooling functions in convolutional neural networks: mixed, gated, and tree. arXiv preprint arXiv:1509.08985 (2015)"},{"key":"39_CR31","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, Granada, Spain, vol. 2011, p. 4 (2011)"},{"key":"39_CR32","unstructured":"Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: BigLearn, NIPS Workshop (2011)"},{"key":"39_CR33","unstructured":"Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 1139\u20131147 (2013)"},{"key":"39_CR34","unstructured":"Gross, S., Wilber, M.: Training and investigating residual nets (2016)"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. arXiv preprint arXiv:1603.05027 (2016)","DOI":"10.1007\/978-3-319-46493-0_38"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2016"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46493-0_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T19:22:00Z","timestamp":1749583320000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46493-0_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319464923","9783319464930"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"17 September 2016","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":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.eccv2016.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"}]}}