{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T03:33:36Z","timestamp":1776569616531,"version":"3.51.2"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031104633","type":"print"},{"value":"9783031104640","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-10464-0_7","type":"book-chapter","created":{"date-parts":[[2022,7,6]],"date-time":"2022-07-06T13:04:06Z","timestamp":1657112646000},"page":"88-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["The Current State of\u00a0the\u00a0Art in\u00a0Deep Learning for\u00a0Image Classification: A Review"],"prefix":"10.1007","author":[{"given":"Adam","family":"Byerly","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatiana","family":"Kalganova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Ott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,7]]},"reference":[{"key":"7_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-319-46478-7_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K Ahmed","year":"2016","unstructured":"Ahmed, K., Baig, M.H., Torresani, L.: Network of experts for large-scale image categorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 516\u2013532. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_32"},{"key":"7_CR2","unstructured":"Bao, H., Dong, L., Furu, W.: BEiT: BERT pre-training of image transformers (2021)"},{"key":"7_CR3","unstructured":"Bernstein, J., Vahdat, A., Yue, Y., Liu, M.-Y.: On the distance between two neural networks and the stability of learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 21370\u201321381 (2020)"},{"key":"7_CR4","unstructured":"Beyer, L., H\u00e9naff, O.J., Kolesnikov, A., Zhai, X., van\u00a0den Oord, A.: Are we done with ImageNet? (2020)"},{"key":"7_CR5","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization (2021)"},{"issue":"9","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1016\/S0893-6080(99)00043-X","volume":"12","author":"K Chen","year":"1999","unstructured":"Chen, K., Xu, L., Chi, H.: Improved learning algorithms for mixture of experts in multiclass classification. Neural Netw. Off. J. Int. Neural Netw. Soc. 12(9), 1229\u20131252 (1999)","journal-title":"Neural Netw. Off. J. Int. Neural Netw. Soc."},{"key":"7_CR7","unstructured":"Choi, D., Passos, A., Shallue, C.J., Dahl, G.E.: Faster neural network training with data echoing (2019)"},{"key":"7_CR8","unstructured":"Chu, X., et al.: Conditional positional encodings for vision transformers (2021)"},{"key":"7_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 Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 3008\u20133017 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"7_CR10","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes (2021)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2010)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: CSWin transformer: a general vision transformer backbone with cross-shaped windows (2021)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"7_CR14","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: ICML 2013 Workshop: Challenges in Representation Learning, July 2013"},{"key":"7_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: Ninth International Conference on Learning Representations (ICLR) (2020)"},{"key":"7_CR16","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: Ninth International Conference on Learning Representations (ICLR) (2020)"},{"key":"7_CR17","unstructured":"Fort, S., Brock, A., Pascanu, R., De, S., Smith, S.L.: Drawing multiple augmentation samples per image during training efficiently decreases test error (2021)"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7_CR19","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian Error Linear Units (GELUs) (2016)"},{"key":"7_CR20","unstructured":"Henighan, T., et al.: Scaling laws for autoregressive generative modeling (2020)"},{"key":"7_CR21","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network (2015)"},{"key":"7_CR22","unstructured":"Hoffer, E., Ben-Nun, T., Hubara, I., Giladi, N., Hoefler, T., Soudry, D.: Augment your batch: better training with larger batches (2019)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7_CR24","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":"7_CR25","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"7_CR26","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization (2018)"},{"issue":"1","key":"7_CR27","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"7_CR28","unstructured":"Jastrz\u0229bski, S., et al.: Three factors influencing minima in SGD. In: International Conference on Artificial Neural Networks and Machine Learning (ICANN) (2018)"},{"key":"7_CR29","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Proceedings of the 38th International Conference on Machine Learning (PMLR) (2021)"},{"key":"7_CR30","unstructured":"Jiang, Z., et al.: All tokens matter: token labeling for training better vision transformers (2021)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Jordan, M.I., Jacobs, R.A.: Hierarchical mixtures of experts and the EM algorithm. In: Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan), vol.\u00a02, pp. 1339\u20131344 (1993)","DOI":"10.1109\/IJCNN.1993.716791"},{"key":"7_CR32","unstructured":"Kaiser, L., Gomez, A.N., Chollet, F.: Depthwise separable convolutions for neural machine translation. In: ICLR 2018 - International Conference on Learning Representations (2018)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Kardas, M., et al.: AxCell: automatic extraction of results from machine learning papers. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pp. 8580\u20138594 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.692"},{"key":"7_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-030-58558-7_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Kolesnikov","year":"2020","unstructured":"Kolesnikov, A., et al.: Big Transfer (BiT): general visual representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 491\u2013507. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_29"},{"key":"7_CR35","unstructured":"Li, Y., Wei, C., Ma, T.: Towards explaining the regularization effect of initial large learning rate in training neural networks. In: Advances in Neural Information Processing Systems (2019)"},{"key":"7_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: The International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Pham, H., Dai, Z., Xie, Q., Luong, M.T., Le, Q.V.: Meta pseudo labels (2020)","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"7_CR38","unstructured":"Qiao, S., Wang, H., Liu, C., Shen, W., Yuille, A.: Micro-batch training with batch-channel normalization and weight standardization (2019)"},{"key":"7_CR39","unstructured":"Ramachandran, P., Bello, I., Parmar, N., Levskaya, A., Vaswani, A., Shlens, J.: Stand-alone self-attention in vision models. In: 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) (2019)"},{"key":"7_CR40","unstructured":"Riquelme, C., et al.: Scaling vision with sparse mixture of experts (2021)"},{"key":"7_CR41","unstructured":"Ryoo, M.S., Piergiovanni, A.J., Arnab, A., Dehghani, M., Angelova, A.: TokenLearner: what can 8 learned tokens do for images and videos? (2021)"},{"issue":"3","key":"7_CR42","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1109\/TIT.1965.1053799","volume":"11","author":"HJ Scudder","year":"1965","unstructured":"Scudder, H.J.: Probability of error of some adaptive pattern-recognition machines. IEEE Trans. Inf. Theory 11(3), 363\u2013371 (1965)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. In: NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 2, pp. 464\u2013468 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"7_CR44","unstructured":"Smith, S.L., Dherin, B., Barrett, D.G.T., De, S.: On the origin of implicit regularization in stochastic gradient descent. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"7_CR45","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, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"7_CR46","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks (2019)"},{"key":"7_CR47","unstructured":"Tan, M., Le, Q.V.: EfficientNetV2: smaller models and faster training (2021)"},{"key":"7_CR48","unstructured":"Tolstikhin, I., et al.: MLP-mixer: an all-MLP architecture for vision (2021)"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G., J\u00e9gou, H.: Going deeper with image transformers. In: The International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"7_CR50","unstructured":"Touvron, H., Vedaldi, A., Douze, M., J\u00e9gou, H.: Fixing the train-test resolution discrepancy. In: Advances in Neural Information Processing Systems (2019)"},{"key":"7_CR51","unstructured":"Touvron, H., Vedaldi, A., Douze, M., J\u00e9gou, H.: Fixing the train-test resolution discrepancy: FixEfficientNet. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"7_CR52","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5999\u20136009 (2017)"},{"key":"7_CR53","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing convolutions to vision transformers. In: The International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"7_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01261-8_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Wu","year":"2018","unstructured":"Wu, Y., He, K.: Group normalization. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_1"},{"key":"7_CR55","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves ImageNet classification. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"7_CR56","unstructured":"You, Y., Gitman, I., Ginsburg, B.: Large batch training of convolutional networks (2017)"},{"key":"7_CR57","unstructured":"You, Y., et al.: Large batch optimization for deep learning: training BERT in 76 minutes. In: Eighth International Conference on Learning Representations (ICLR) (2019)"},{"key":"7_CR58","doi-asserted-by":"crossref","unstructured":"Yuan, L., Hou, Q., Jiang, Z., Feng, J., Yan, S.: VOLO: Vision outlooker for visual recognition (2021)","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"7_CR59","doi-asserted-by":"crossref","unstructured":"Zhai, X., Kolesnikov, A., Houlsby, N., Beyer, L.: Scaling vision transformers (2021)","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"7_CR60","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: Mixup. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"7_CR61","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. In: 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings (2017)"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-10464-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T16:11:28Z","timestamp":1727539888000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-10464-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031104633","9783031104640"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-10464-0_7","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"value":"2367-3370","type":"print"},{"value":"2367-3389","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"7 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Science and Information Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/saiconference.com\/Computing","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}