{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T19:04:08Z","timestamp":1789758248807,"version":"4.0.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T00:00:00Z","timestamp":1688083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Softw Tools Technol Transfer"],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. We consider the problem of monitoring the classification decisions of neural networks in the presence of novel classes. For this purpose, we generalize our recently proposed abstraction-based monitor from binary output to real-valued quantitative output. This quantitative output enables new applications, two of which we investigate in the paper. As our first application, we introduce an algorithmic framework for active monitoring of a neural network, which allows us to learn new classes dynamically and yet maintain high monitoring performance. As our second application, we present an offline procedure to retrain the neural network to improve the monitor\u2019s detection performance without deteriorating the network\u2019s classification accuracy. Our experimental evaluation demonstrates both the benefits of our active monitoring framework in dynamic scenarios and the effectiveness of the retraining procedure.<\/jats:p>","DOI":"10.1007\/s10009-023-00711-4","type":"journal-article","created":{"date-parts":[[2023,6,30]],"date-time":"2023-06-30T13:01:31Z","timestamp":1688130091000},"page":"575-592","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Into the unknown: active monitoring of neural networks (extended version)"],"prefix":"10.1007","volume":"25","author":[{"given":"Konstantin","family":"Kueffner","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9525-0333","authenticated-orcid":false,"given":"Anna","family":"Lukina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3658-1065","authenticated-orcid":false,"given":"Christian","family":"Schilling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2985-7724","authenticated-orcid":false,"given":"Thomas A.","family":"Henzinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,30]]},"reference":[{"key":"711_CR1","doi-asserted-by":"publisher","first-page":"1893","DOI":"10.1109\/CVPR.2015.7298799","volume-title":"CVPR","author":"A. Bendale","year":"2015","unstructured":"Bendale, A., Boult, T.E.: Towards open world recognition. In: CVPR, pp.\u00a01893\u20131902. IEEE Comput. Soc., Los Alamitos (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298799"},{"key":"711_CR2","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1109\/CVPR.2016.173","volume-title":"CVPR","author":"A. Bendale","year":"2016","unstructured":"Bendale, A., Boult, T.E.: Towards open set deep networks. In: CVPR, pp.\u00a01563\u20131572. IEEE Comput. Soc., Los Alamitos (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.173"},{"key":"711_CR3","unstructured":"Bendre, N., Terashima-Mar\u00edn, H., Najafirad, P.: Learning from few samples: a survey (2020). https:\/\/arxiv.org\/abs\/2007.15484. arXiv:2007.15484. CoRR"},{"key":"711_CR4","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-7908-2604-3_16","volume-title":"COMPSTAT","author":"L. Bottou","year":"2010","unstructured":"Bottou, L.: Large-scale machine learning with stochastic gradient descent. In: COMPSTAT, pp.\u00a0177\u2013186. Physica-Verlag, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-7908-2604-3_16"},{"key":"711_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Cheng, C., Yan, J., et\u00a0al.: Monitoring object detection abnormalities via data-label and post-algorithm abstractions (2021). https:\/\/arxiv.org\/abs\/2103.15456. arXiv:2103.15456. CoRR","DOI":"10.1109\/IROS51168.2021.9636713"},{"key":"711_CR6","doi-asserted-by":"publisher","first-page":"300","DOI":"10.23919\/DATE.2019.8714971","volume-title":"DATE","author":"C. Cheng","year":"2019","unstructured":"Cheng, C., N\u00fchrenberg, G., Yasuoka, H.: Runtime monitoring neuron activation patterns. In: DATE, IEEE, Florence, Italy, pp.\u00a0300\u2013303 (2019). https:\/\/doi.org\/10.23919\/DATE.2019.8714971"},{"key":"711_CR7","doi-asserted-by":"publisher","first-page":"2921","DOI":"10.1109\/IJCNN.2017.7966217","volume-title":"IJCNN","author":"G. Cohen","year":"2017","unstructured":"Cohen, G., Afshar, S., Tapson, J., et al.: EMNIST: extending MNIST to handwritten letters. In: IJCNN, pp.\u00a02921\u20132926. IEEE, Anchorage, AK, USA (2017). https:\/\/doi.org\/10.1109\/IJCNN.2017.7966217"},{"issue":"2","key":"711_CR8","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/BF00993277","volume":"15","author":"D.A. Cohn","year":"1994","unstructured":"Cohn, D.A., Atlas, L.E., Ladner, R.E.: Improving generalization with active learning. Mach. Learn. 15(2), 201\u2013221 (1994). https:\/\/doi.org\/10.1007\/BF00993277","journal-title":"Mach. Learn."},{"key":"711_CR9","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1109\/ICDM.2016.0102","volume-title":"ICDM","author":"S. Das","year":"2016","unstructured":"Das, S., Wong, W., Dietterich, T.G., et al.: Incorporating expert feedback into active anomaly discovery. In: ICDM, pp.\u00a0853\u2013858. IEEE Comput. Soc., Los Alamitos (2016). https:\/\/doi.org\/10.1109\/ICDM.2016.0102"},{"key":"711_CR10","first-page":"7367","volume-title":"AAAI","author":"J. Fan","year":"2021","unstructured":"Fan, J., Li, W.: Adversarial training and provable robustness: a tale of two objectives. In: AAAI, pp.\u00a07367\u20137376. AAAI Press, Menlo Park (2021). https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/16904"},{"key":"711_CR11","series-title":"JMLR Workshop and Conference Proceedings","first-page":"1050","volume-title":"ICML","author":"Y. Gal","year":"2016","unstructured":"Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: ICML, JMLR Workshop and Conference Proceedings, vol.\u00a048. JMLR.org, New York, NY, USA, pp.\u00a01050\u20131059 (2016). http:\/\/proceedings.mlr.press\/v48\/gal16.html"},{"key":"711_CR12","first-page":"4878","volume-title":"NeurIPS","author":"Y. Geifman","year":"2017","unstructured":"Geifman, Y., El-Yaniv, R.: Selective classification for deep neural networks. In: NeurIPS, pp.\u00a04878\u20134887 (2017). http:\/\/papers.nips.cc\/paper\/7073-selective-classification-for-deep-neural-networks"},{"key":"711_CR13","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717761","volume-title":"Evaluating Derivatives - Principles and Techniques of Algorithmic Differentiation","author":"A. Griewank","year":"2008","unstructured":"Griewank, A., Walther, A.: Evaluating Derivatives - Principles and Techniques of Algorithmic Differentiation. SIAM, Philadelphia (2008). https:\/\/doi.org\/10.1137\/1.9780898717761"},{"key":"711_CR14","volume-title":"ICLR. OpenReview.net","author":"S. Guerriero","year":"2018","unstructured":"Guerriero, S., Caputo, B., Mensink, T.: DeepNCM: deep nearest class mean classifiers. In: ICLR. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=rkPLZ4JPM"},{"key":"711_CR15","series-title":"PMLR","first-page":"1321","volume-title":"ICML","author":"C. Guo","year":"2017","unstructured":"Guo, C., Pleiss, G., Sun, Y., et al.: On calibration of modern neural networks. In: ICML, PMLR, vol.\u00a070. PMLR, Sydney, Australia, pp.\u00a01321\u20131330 (2017). http:\/\/proceedings.mlr.press\/v70\/guo17a.html"},{"key":"711_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ITSC45102.2020.9294609","volume-title":"ITSC","author":"A. Gupta","year":"2020","unstructured":"Gupta, A., Carlone, L.: Online monitoring for neural network based monocular pedestrian pose estimation. In: ITSC, pp.\u00a01\u20138. IEEE, Rhodes, Greece (2020). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294609"},{"key":"711_CR17","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/978-3-030-88494-9_14","volume-title":"RV","author":"V. Hashemi","year":"2021","unstructured":"Hashemi, V., Kret\u00ednsk\u00fd, J., Mohr, S., et al.: Gaussian-based runtime detection of out-of-distribution inputs for neural networks. In: RV, LNCS, vol.\u00a012974, pp.\u00a0254\u2013264. Springer, Berlin (2021). https:\/\/doi.org\/10.1007\/978-3-030-88494-9_14"},{"key":"711_CR18","volume-title":"ICLR. OpenReview.net","author":"D. Hendrycks","year":"2017","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR. OpenReview.net (2017). https:\/\/openreview.net\/forum?id=Hkg4TI9xl"},{"key":"711_CR19","series-title":"Frontiers in Artificial Intelligence and Applications","doi-asserted-by":"publisher","first-page":"2433","DOI":"10.3233\/FAIA200375","volume-title":"ECAI","author":"T.A. Henzinger","year":"2020","unstructured":"Henzinger, T.A., Lukina, A., Schilling, C.: Outside the box: abstraction-based monitoring of neural networks. In: ECAI, Frontiers in Artificial Intelligence and Applications, vol.\u00a0325, pp.\u00a02433\u20132440. IOS Press, Amsterdam (2020). https:\/\/doi.org\/10.3233\/FAIA200375"},{"key":"711_CR20","unstructured":"Ibrahim, S.H., Nassar, M.: Hack the box: Fooling deep learning abstraction-based monitors (2021). https:\/\/arxiv.org\/abs\/2107.04764. arXiv:2107.04764. CoRR"},{"key":"711_CR21","series-title":"Springer Series in Statistics","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1904-8","volume-title":"Principal Component Analysis","author":"I.T. Jolliffe","year":"1986","unstructured":"Jolliffe, I.T.: Principal Component Analysis. Springer Series in Statistics. Springer, Berlin (1986). https:\/\/doi.org\/10.1007\/978-1-4757-1904-8"},{"key":"711_CR22","first-page":"219","volume-title":"KDD","author":"E.M. Knorr","year":"1997","unstructured":"Knorr, E.M., Ng, R.T.: A unified notion of outliers: properties and computation. In: KDD, pp.\u00a0219\u2013222. AAAI Press, Menlo Park (1997). http:\/\/www.aaai.org\/Library\/KDD\/1997\/kdd97-044.php"},{"key":"711_CR23","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images (2009). Tech. Rep. http:\/\/www.cs.Toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"issue":"11","key":"711_CR24","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y. LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"711_CR25","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2016.12.038","volume":"234","author":"W. Liu","year":"2017","unstructured":"Liu, W., Wang, Z., Liu, X., et al.: A survey of deep neural network architectures and their applications. Neurocomputing 234, 11\u201326 (2017). https:\/\/doi.org\/10.1016\/j.neucom.2016.12.038","journal-title":"Neurocomputing"},{"issue":"2","key":"711_CR26","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S.P. Lloyd","year":"1982","unstructured":"Lloyd, S.P.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013136 (1982). https:\/\/doi.org\/10.1109\/TIT.1982.1056489","journal-title":"IEEE Trans. Inf. Theory"},{"key":"711_CR27","unstructured":"Lu, J., Gong, P., Ye, J., et\u00a0al.: Learning from very few samples: a survey (2020). https:\/\/arxiv.org\/abs\/2009.02653. arXiv:2009.02653. CoRR"},{"key":"711_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/978-3-030-88494-9_3","volume-title":"RV","author":"A. Lukina","year":"2021","unstructured":"Lukina, A., Schilling, C., Henzinger, T.A.: Into the unknown: active monitoring of neural networks. In: RV, LNCS, vol.\u00a012974, pp.\u00a042\u201361. Springer, Berlin (2021). https:\/\/doi.org\/10.1007\/978-3-030-88494-9_3"},{"key":"711_CR29","doi-asserted-by":"publisher","first-page":"9537","DOI":"10.1109\/ICRA.2019.8793803","volume-title":"ICRA","author":"M. Mancini","year":"2019","unstructured":"Mancini, M., Karaoguz, H., Ricci, E., et al.: Knowledge is never enough: towards web aided deep open world recognition. In: ICRA, pp.\u00a09537\u20139543. IEEE, Montreal, QC, Canada (2019). https:\/\/doi.org\/10.1109\/ICRA.2019.8793803"},{"key":"711_CR30","unstructured":"Mandelbaum, A., Weinshall, D.: Distance-based confidence score for neural network classifiers (2017). http:\/\/arxiv.org\/abs\/1709.09844. arXiv:1709.09844. CoRR"},{"key":"711_CR31","first-page":"109","volume-title":"Psychology of Learning and Motivation","author":"M. McCloskey","year":"1989","unstructured":"McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Psychology of Learning and Motivation, vol.\u00a024, pp.\u00a0109\u2013165. Elsevier, Amsterdam (1989). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0079742108605368"},{"issue":"11","key":"711_CR32","doi-asserted-by":"publisher","first-page":"2624","DOI":"10.1109\/TPAMI.2013.83","volume":"35","author":"T. Mensink","year":"2013","unstructured":"Mensink, T., Verbeek, J.J., Perronnin, F., et al.: Distance-based image classification: generalizing to new classes at near-zero cost. IEEE Trans. Pattern Anal. Mach. Intell. 35(11), 2624\u20132637 (2013). https:\/\/doi.org\/10.1109\/TPAMI.2013.83","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"711_CR33","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"S.J. Pan","year":"2010","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2010). https:\/\/doi.org\/10.1109\/TKDE.2009.191","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"711_CR34","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","volume":"113","author":"G.I. Parisi","year":"2019","unstructured":"Parisi, G.I., Kemker, R., Part, J.L., et al.: Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54\u201371 (2019). https:\/\/doi.org\/10.1016\/j.neunet.2019.01.012","journal-title":"Neural Netw."},{"key":"711_CR35","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.sigpro.2013.12.026","volume":"99","author":"M.A.F. Pimentel","year":"2014","unstructured":"Pimentel, M.A.F., Clifton, D.A., Clifton, L.A., et al.: A review of novelty detection. Signal Process. 99, 215\u2013249 (2014). https:\/\/doi.org\/10.1016\/j.sigpro.2013.12.026","journal-title":"Signal Process."},{"key":"711_CR36","doi-asserted-by":"publisher","first-page":"20,067","DOI":"10.1109\/ACCESS.2021.3055015","volume":"9","author":"Q.M. Rahman","year":"2021","unstructured":"Rahman, Q.M., Corke, P., Dayoub, F.: Run-time monitoring of machine learning for robotic perception: a survey of emerging trends. IEEE Access 9, 20,067\u201320,075 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3055015","journal-title":"IEEE Access"},{"key":"711_CR37","doi-asserted-by":"publisher","first-page":"5533","DOI":"10.1109\/CVPR.2017.587","volume-title":"CVPR","author":"S. Rebuffi","year":"2017","unstructured":"Rebuffi, S., Kolesnikov, A., Sperl, G., et al.: iCaRL: incremental classifier and representation learning. In: CVPR, pp.\u00a05533\u20135542. IEEE Comput. Soc., Los Alamitos (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.587"},{"key":"711_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/C2016-0-05108-2","volume-title":"Advances in Domain Adaptation Theory","author":"I. Redko","year":"2019","unstructured":"Redko, I., Morvant, E., Habrard, A., et al.: Advances in Domain Adaptation Theory. Elsevier, Amsterdam (2019). https:\/\/doi.org\/10.1016\/C2016-0-05108-2"},{"key":"711_CR39","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1109\/CVPR.2015.7298746","volume-title":"CVPR","author":"A. Royer","year":"2015","unstructured":"Royer, A., Lampert, C.H.: Classifier adaptation at prediction time. In: CVPR, IEEE Comput. Soc., Los Alamitos, pp.\u00a01401\u20131409 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298746"},{"key":"711_CR40","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1007\/BFb0020217","volume-title":"ICANN","author":"B. Sch\u00f6lkopf","year":"1997","unstructured":"Sch\u00f6lkopf, B., Smola, A.J., M\u00fcller, K.: Kernel principal component analysis. In: ICANN, LNCS, vol.\u00a01327, pp.\u00a0583\u2013588. Springer, Berlin (1997). https:\/\/doi.org\/10.1007\/BFb0020217"},{"key":"711_CR41","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1007\/978-3-319-66709-6_19","volume-title":"GCPR","author":"A. Schultheiss","year":"2017","unstructured":"Schultheiss, A., K\u00e4ding, C., Freytag, A., et al.: Finding the unknown: novelty detection with extreme value signatures of deep neural activations. In: GCPR, LNCS, vol.\u00a010496, pp.\u00a0226\u2013238. Springer, Berlin (2017). https:\/\/doi.org\/10.1007\/978-3-319-66709-6_19"},{"key":"711_CR42","series-title":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi-asserted-by":"publisher","DOI":"10.2200\/S00429ED1V01Y201207AIM018","volume-title":"Active Learning","author":"B. Settles","year":"2012","unstructured":"Settles, B.: Active Learning, Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan Kaufmann, San Mateo (2012). https:\/\/doi.org\/10.2200\/S00429ED1V01Y201207AIM018"},{"key":"711_CR43","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1109\/IJCNN.2011.6033395","volume-title":"IJCNN","author":"J. Stallkamp","year":"2011","unstructured":"Stallkamp, J., Schlipsing, M., Salmen, J., et al.: The German traffic sign recognition benchmark: a multi-class classification competition. In: IJCNN, pp.\u00a01453\u20131460. IEEE, San Jose, CA, USA (2011). https:\/\/doi.org\/10.1109\/IJCNN.2011.6033395"},{"issue":"4","key":"711_CR44","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1007\/s11263-019-01232-x","volume":"128","author":"R. Sun","year":"2020","unstructured":"Sun, R., Lampert, C.H.: Ks(conf): a light-weight test if a multiclass classifier operates outside of its specifications. Int. J. Comput. Vis. 128(4), 970\u2013995 (2020). https:\/\/doi.org\/10.1007\/s11263-019-01232-x","journal-title":"Int. J. Comput. Vis."},{"key":"711_CR45","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01424-7_27","volume-title":"ICANN","author":"C. Tan","year":"2018","unstructured":"Tan, C., Sun, F., Kong, T., et al.: A survey on deep transfer learning. In: ICANN, LNCS, vol.\u00a011141, pp.\u00a0270\u2013279. Springer, Berlin (2018). https:\/\/doi.org\/10.1007\/978-3-030-01424-7_27"},{"key":"711_CR46","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/IROS.2017.8202133","volume-title":"IROS","author":"J. Tobin","year":"2017","unstructured":"Tobin, J., Fong, R., Ray, A., et al.: Domain randomization for transferring deep neural networks from simulation to the real world. In: IROS, pp.\u00a023\u201330. IEEE, Vancouver, BC, Canada (2017). https:\/\/doi.org\/10.1109\/IROS.2017.8202133"},{"key":"711_CR47","unstructured":"Wagstaff, K.L., Lu, S.: Efficient active learning for new domains (2020). In: Workshop on real world experiment design and active learning"},{"key":"711_CR48","unstructured":"Wu, C., Falcone, Y., Bensalem, S.: Customizable reference runtime monitoring of neural networks using resolution boxes (2021). https:\/\/arxiv.org\/abs\/2104.14435. arXiv:2104.14435. CoRR"},{"key":"711_CR49","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms (2017). http:\/\/arxiv.org\/abs\/1708.07747. arXiv:1708.07747. CoRR"},{"key":"711_CR50","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"ECCV","author":"M.D. Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: ECCV, LNCS, vol.\u00a08689, pp.\u00a0818\u2013833. Springer, Berlin (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"711_CR51","doi-asserted-by":"publisher","first-page":"3566","DOI":"10.1109\/CVPR.2014.456","volume-title":"CVPR","author":"P. Zhang","year":"2014","unstructured":"Zhang, P., Wang, J., Farhadi, A., et al.: Predicting failures of vision systems. In: CVPR, pp.\u00a03566\u20133573. IEEE Comput. Soc., Los Alamitos (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.456"},{"issue":"10","key":"711_CR52","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1109\/TPAMI.2015.2502579","volume":"38","author":"X. Zhang","year":"2016","unstructured":"Zhang, X., Zou, J., He, K., et al.: Accelerating very deep convolutional networks for classification and detection. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 1943\u20131955 (2016). https:\/\/doi.org\/10.1109\/TPAMI.2015.2502579","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"711_CR53","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1109\/ISSRE52982.2021.00027","volume-title":"ISSRE","author":"Z. Zhang","year":"2021","unstructured":"Zhang, Z., Wu, P., Chen, Y., et al.: Out-of-distribution detection through relative activation-deactivation abstractions. In: ISSRE, pp.\u00a0150\u2013161. IEEE, Wuhan, China (2021). https:\/\/doi.org\/10.1109\/ISSRE52982.2021.00027"},{"key":"711_CR54","first-page":"1231","volume-title":"ICML","author":"P. Zhao","year":"2010","unstructured":"Zhao, P., Hoi, S.C.H.: OTL: a framework of online transfer learning. In: ICML, Omnipress, Haifa, Israel pp.\u00a01231\u20131238 (2010). https:\/\/icml.cc\/Conferences\/2010\/papers\/219.pdf"}],"container-title":["International Journal on Software Tools for Technology Transfer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10009-023-00711-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10009-023-00711-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10009-023-00711-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T09:05:10Z","timestamp":1699520710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10009-023-00711-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,30]]},"references-count":54,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["711"],"URL":"https:\/\/doi.org\/10.1007\/s10009-023-00711-4","relation":{},"ISSN":["1433-2779","1433-2787"],"issn-type":[{"value":"1433-2779","type":"print"},{"value":"1433-2787","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,30]]},"assertion":[{"value":"30 May 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}