{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:56:10Z","timestamp":1775325370713,"version":"3.50.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:00:00Z","timestamp":1643328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072190"],"award-info":[{"award-number":["62072190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61836003 (key project)"],"award-info":[{"award-number":["61836003 (key project)"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10994-021-06074-8","type":"journal-article","created":{"date-parts":[[2022,1,28]],"date-time":"2022-01-28T00:04:01Z","timestamp":1643328241000},"page":"1159-1179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Towards interpreting deep neural networks via layer behavior understanding"],"prefix":"10.1007","volume":"111","author":[{"given":"Jiezhang","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jincheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangmiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,28]]},"reference":[{"key":"6074_CR1","unstructured":"Alain G, Bengio Y (2016) Understanding intermediate layers using linear classifier probes. arXiv preprint arXiv:1610.01644"},{"key":"6074_CR2","unstructured":"Bang S, Xie P, Wu W, Xing E (2019) Explaining a black-box using deep variational information bottleneck approach. arXiv preprint arXiv:1902.06918"},{"key":"6074_CR4","doi-asserted-by":"crossref","unstructured":"Bau D, Zhou B, Khosla A, Oliva A, Torralba A (2017) Network dissection: Quantifying interpretability of deep visual representations. In: IEEE Conference on computer vision and pattern recognition, pp 6541\u20136549","DOI":"10.1109\/CVPR.2017.354"},{"key":"6074_CR6","unstructured":"Bjorck N, Gomes CP, Selman B, Weinberger KQ (2018) Understanding batch normalization. In: Advances in neural information processing systems, pp 7694\u20137705"},{"key":"6074_CR7","unstructured":"Brock A, Donahue J, Simonyan K (2019) Large scale GAN training for high fidelity natural image synthesis. In: International conference on learning representations."},{"key":"6074_CR8","unstructured":"Chen CFR, Fan Q, Mallinar N, Sercu T, Feris R (2019a) Big-little net: An efficient multi-scale feature representation for visual and speech recognition. In: International conference on learning representations."},{"issue":"1","key":"6074_CR9","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1109\/TNNLS.2020.2978753","volume":"32","author":"Z Chen","year":"2020","unstructured":"Chen, Z., Deng, L., Li, G., Sun, J., Hu, X., Liang, L., et al. (2020). Effective and efficient batch normalization using a few uncorrelated data for statistics estimation. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 348\u2013362.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6074_CR10","doi-asserted-by":"crossref","unstructured":"Chen ZM, Wei XS, Jin X, Guo Y (2019b) Multi-label image recognition with joint class-aware map disentangling and label correlation embedding. In: IEEE international conference on multimedia and expo, pp 622\u2013627","DOI":"10.1109\/ICME.2019.00113"},{"key":"6074_CR11","doi-asserted-by":"crossref","unstructured":"Chen ZM, Wei XS, Wang P, Guo Y (2019c) Multi-label image recognition with graph convolutional networks. In: IEEE conference on computer vision and pattern recognition, pp 5177\u20135186","DOI":"10.1109\/CVPR.2019.00532"},{"key":"6074_CR12","first-page":"2292","volume":"26","author":"M Cuturi","year":"2013","unstructured":"Cuturi, M. (2013). Sinkhorn distances: Lightspeed computation of optimal transport. Advances in Neural Information Processing Systems, 26, 2292\u20132300.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6074_CR13","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition, pp. 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"6074_CR14","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6074_CR15","doi-asserted-by":"crossref","unstructured":"Dosovitskiy A, Brox T (2016) Inverting visual representations with convolutional networks. In: IEEE conference on computer vision and pattern recognition, pp. 4829\u20134837","DOI":"10.1109\/CVPR.2016.522"},{"key":"6074_CR16","doi-asserted-by":"crossref","unstructured":"Durand T, Mehrasa N, Mori G (2019) Learning a deep convnet for multi-label classification with partial labels. In: IEEE conference on computer vision and pattern recognition, pp. 647\u2013657","DOI":"10.1109\/CVPR.2019.00074"},{"issue":"2","key":"6074_CR17","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2010). The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2), 303\u2013338.","journal-title":"International Journal of Computer Vision"},{"key":"6074_CR18","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.neunet.2020.03.025","volume":"127","author":"X Fang","year":"2020","unstructured":"Fang, X., Bai, H., Guo, Z., Shen, B., & Xu, Z. (2020). Dart: Domain-adversarial residual-transfer networks for unsupervised cross-domain image classification. Neural Networks, 127, 182\u2013192.","journal-title":"Neural Networks"},{"key":"6074_CR19","unstructured":"Frogner C, Zhang C, Mobahi H, Araya M, Poggio TA (2015) Learning with a wasserstein loss. In: Advances in neural information processing systems, pp 2053\u20132061"},{"key":"6074_CR21","unstructured":"Genevay A, Peyr\u00e9 G, Cuturi M (2018) Learning generative models with sinkhorn divergences. In: Artificial intelligence and statistics"},{"issue":"7","key":"6074_CR22","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/TKDE.2016.2545658","volume":"28","author":"X Geng","year":"2016","unstructured":"Geng, X. (2016). Label distribution learning. IEEE Transactions on Knowledge and Data Engineering, 28(7), 1734\u20131748.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"6074_CR23","doi-asserted-by":"publisher","first-page":"124010","DOI":"10.1088\/1742-5468\/abc61e","volume":"12","author":"S Goldt","year":"2020","unstructured":"Goldt, S., Advani, M. S., Saxe, A. M., Krzakala, F., & Zdeborov\u00e1, L. (2020). Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. Journal of Statistical Mechanics: Theory and Experiment, 12, 124010.","journal-title":"Journal of Statistical Mechanics: Theory and Experiment"},{"key":"6074_CR24","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.neunet.2020.03.001","volume":"126","author":"Y Guo","year":"2020","unstructured":"Guo, Y., Chen, J., Du, Q., Hengel, A. V. D., Shi, Q., & Tan, M. (2020). Multi-way backpropagation for training compact deep neural networks. Neural Networks, 126, 250\u2013261.","journal-title":"Neural Networks"},{"key":"6074_CR25","doi-asserted-by":"crossref","unstructured":"Gupta P, Sch\u00fctze H (2018) Lisa: Explaining recurrent neural network judgments via layer-wise semantic accumulation and example to pattern transformation. In: Empirical methods in natural language processing workshop BlackboxNLP.","DOI":"10.18653\/v1\/W18-5418"},{"key":"6074_CR26","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6074_CR27","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/j.neunet.2020.09.007","volume":"132","author":"S Hussain","year":"2020","unstructured":"Hussain, S., Anees, A., Das, A., Nguyen, B. P., Marzuki, M., Lin, S., et al. (2020). High-content image generation for drug discovery using generative adversarial networks. Neural Networks, 132, 353\u2013363.","journal-title":"Neural Networks"},{"key":"6074_CR28","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning"},{"key":"6074_CR29","first-page":"3301","volume":"97","author":"Y Kaya","year":"2019","unstructured":"Kaya, Y., Hong, S., & Dumitras, T. (2019). Shallow-deep networks: Understanding and mitigating network overthinking. International Conference on Machine Learning, 97, 3301\u20133310.","journal-title":"International Conference on Machine Learning"},{"issue":"1","key":"6074_CR30","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1137\/060659624","volume":"30","author":"PA Knight","year":"2008","unstructured":"Knight, P. A. (2008). The sinkhorn-knopp algorithm: Convergence and applications. SIAM Journal on Matrix Analysis and Applications, 30(1), 261\u2013275.","journal-title":"SIAM Journal on Matrix Analysis and Applications"},{"key":"6074_CR31","unstructured":"Lee CY, Xie S, Gallagher P, Zhang Z, Tu Z (2015) Deeply-supervised nets. In: Artificial intelligence and statistics, pp 562\u2013570"},{"issue":"10","key":"6074_CR32","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/2001269.2001295","volume":"54","author":"H Lee","year":"2011","unstructured":"Lee, H., Grosse, R., Ranganath, R., & Ng, A. Y. (2011). Unsupervised learning of hierarchical representations with convolutional deep belief networks. Communications of the ACM, 54(10), 95\u2013103.","journal-title":"Communications of the ACM"},{"key":"6074_CR33","first-page":"1271","volume":"65","author":"H Lee","year":"2017","unstructured":"Lee, H., Ge, R., Ma, T., Risteski, A., & Arora, S. (2017). On the ability of neural nets to express distributions. Proceedings of the Conference on Learning Theory, 65, 1271\u20131296.","journal-title":"Proceedings of the Conference on Learning Theory"},{"key":"6074_CR34","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.neunet.2020.08.011","volume":"132","author":"W Li","year":"2020","unstructured":"Li, W., Xiong, W., Liao, H., Huo, J., & Luo, J. (2020). Carigan: Caricature generation through weakly paired adversarial learning. Neural Networks, 132, 66\u201374.","journal-title":"Neural Networks"},{"key":"6074_CR36","doi-asserted-by":"crossref","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: International conference on computer vision","DOI":"10.1109\/ICCV.1999.790410"},{"key":"6074_CR37","unstructured":"Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: International conference on machine learning"},{"key":"6074_CR38","doi-asserted-by":"crossref","unstructured":"Mahendran A, Vedaldi A (2015) Understanding deep image representations by inverting them. In: IEEE conference on computer vision and pattern recognition, pp 5188\u20135196","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"6074_CR39","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111\u20133119"},{"issue":"9","key":"6074_CR40","first-page":"2563","volume":"12","author":"G Montavon","year":"2011","unstructured":"Montavon, G., Braun, M. L., & M\u00fcller, K. R. (2011). Kernel analysis of deep networks. Journal of Machine Learning Research, 12(9), 2563\u20132581.","journal-title":"Journal of Machine Learning Research"},{"key":"6074_CR41","unstructured":"Papernot N, McDaniel P (2018) Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning. arXiv preprint arXiv:1803.04765"},{"issue":"5","key":"6074_CR42","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","volume":"11","author":"G Peyr\u00e9","year":"2019","unstructured":"Peyr\u00e9, G., Cuturi, M., et al. (2019). Computational optimal transport: With applications to data science. Foundations and Trends\u00ae in Machine Learning, 11(5), 355\u2013607.","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"6074_CR43","unstructured":"Raghu M, Gilmer J, Yosinski J, Sohl-Dickstein J (2017) Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability. In: Advances in neural information processing systems, pp 6076\u20136085"},{"key":"6074_CR44","unstructured":"Santurkar S, Tsipras D, Ilyas A, Madry A (2018) How does batch normalization help optimization? In: Advances in neural information processing systems, pp 2483\u20132493"},{"key":"6074_CR45","doi-asserted-by":"crossref","unstructured":"Saxe AM, Bansal Y, Dapello J, Advani M, Kolchinsky A, Tracey BD, Cox DD (2018) On the information bottleneck theory of deep learning. In: International conference on learning representations.","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"6074_CR46","doi-asserted-by":"crossref","unstructured":"Scardapane S, Scarpiniti M, Baccarelli E, Uncini A (2020) Why should we add early exits to neural networks? arXiv preprint arXiv:2004.12814","DOI":"10.1007\/s12559-020-09734-4"},{"issue":"7","key":"6074_CR47","first-page":"2896","volume":"29","author":"W Shi","year":"2018","unstructured":"Shi, W., Gong, Y., Tao, X., & Zheng, N. (2018). Training dcnn by combining max-margin, max-correlation objectives, and correntropy loss for multilabel image classification. IEEE Transactions on Neural Networks and Learning Systems, 29(7), 2896\u20132908.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"6074_CR48","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations."},{"issue":"1","key":"6074_CR49","first-page":"31","volume":"20","author":"S Sonoda","year":"2019","unstructured":"Sonoda, S., & Murata, N. (2019). Transport analysis of infinitely deep neural network. The Journal of Machine Learning Research, 20(1), 31\u201382.","journal-title":"The Journal of Machine Learning Research"},{"key":"6074_CR50","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.neunet.2019.11.003","volume":"122","author":"J Sun","year":"2019","unstructured":"Sun, J., Zhong, G., Chen, Y., Liu, Y., & Huang, K. (2019). Generative adversarial networks with mixture of t-distributions noise for diverse image generation. Neural Networks, 122, 374\u2013381.","journal-title":"Neural Networks"},{"key":"6074_CR51","unstructured":"Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2014) Intriguing properties of neural networks. In: International conference on learning representations."},{"key":"6074_CR52","unstructured":"Tian Y (2017) An analytical formula of population gradient for two-layered relu network and its applications in convergence and critical point analysis. In: International conference on machine learning."},{"key":"6074_CR53","doi-asserted-by":"crossref","unstructured":"Tishby N, Zaslavsky N (2015) Deep learning and the information bottleneck principle. In: IEEE Information theory workshop, pp 1\u20135.","DOI":"10.1109\/ITW.2015.7133169"},{"key":"6074_CR54","volume-title":"Optimal transport: Old and new","author":"C Villani","year":"2008","unstructured":"Villani, C. (2008). Optimal transport: Old and new (Vol. 338). Berlin: Springer."},{"key":"6074_CR55","doi-asserted-by":"crossref","unstructured":"Wang J, Yang Y, Mao J, Huang Z, Huang C, Xu W (2016) Cnn-rnn: A unified framework for multi-label image classification. In: IEEE conference on computer vision and pattern recognition, pp 2285\u20132294.","DOI":"10.1109\/CVPR.2016.251"},{"issue":"12","key":"6074_CR56","doi-asserted-by":"publisher","first-page":"2349","DOI":"10.1007\/s10994-020-05916-1","volume":"109","author":"L Wang","year":"2020","unstructured":"Wang, L., Zhang, H., Yi, J., Hsieh, C. J., & Jiang, Y. (2020). Spanning attack: Reinforce black-box attacks with unlabeled data. Machine Learning, 109(12), 2349\u20132368.","journal-title":"Machine Learning"},{"issue":"7","key":"6074_CR57","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/TNNLS.2018.2876179","volume":"30","author":"S Wu","year":"2019","unstructured":"Wu, S., Li, G., Deng, L., Liu, L., Wu, D., Xie, Y., & Shi, L. (2019). $$l1$$ -norm batch normalization for efficient training of deep neural networks. IEEE Transactions on Neural Networks and Learning Systems, 30(7), 2043\u20132051.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"6074_CR58","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/s10994-019-05838-7","volume":"109","author":"HJ Ye","year":"2020","unstructured":"Ye, H. J., Sheng, X. R., & Zhan, D. C. (2020). Few-shot learning with adaptively initialized task optimizer: A practical meta-learning approach. Machine Learning, 109(3), 643\u2013664.","journal-title":"Machine Learning"},{"key":"6074_CR59","unstructured":"Yeh CK, Chen J, Yu C, Yu D (2019) Unsupervised speech recognition via segmental empirical output distribution matching. In: International conference on learning representations."},{"key":"6074_CR60","unstructured":"Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H (2015) Understanding neural networks through deep visualization. In: International conference on machine learning workshop."},{"key":"6074_CR61","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision, pp 818\u2013833.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"6074_CR62","doi-asserted-by":"crossref","unstructured":"Zhang Q, Cao R, Shi F, Wu YN, Zhu SC (2018) Interpreting cnn knowledge via an explanatory graph. In: AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11819"},{"key":"6074_CR63","doi-asserted-by":"crossref","unstructured":"Zhang Q, Yang Y, Ma H, Wu YN (2019) Interpreting cnns via decision trees. In: IEEE conference on computer vision and pattern recognition, pp 6261\u20136270.","DOI":"10.1109\/CVPR.2019.00642"},{"issue":"3","key":"6074_CR64","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/s10994-019-05839-6","volume":"109","author":"D Zou","year":"2020","unstructured":"Zou, D., Cao, Y., Zhou, D., & Gu, Q. (2020). Gradient descent optimizes over-parameterized deep relu networks. Machine Learning, 109(3), 467\u2013492.","journal-title":"Machine Learning"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06074-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-021-06074-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-021-06074-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T03:10:14Z","timestamp":1674875414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-021-06074-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,28]]},"references-count":60,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["6074"],"URL":"https:\/\/doi.org\/10.1007\/s10994-021-06074-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,28]]},"assertion":[{"value":"19 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}