{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T18:23:52Z","timestamp":1790360632109,"version":"4.1.0"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:00:00Z","timestamp":1659657600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:00:00Z","timestamp":1659657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universit\u00e0 degli Studi di Roma La Sapienza"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep neural networks are the driving force of the recent explosion of machine learning applications in everyday life. However, they usually require a lot of training data to work well, and they act as black-boxes, making predictions without any explanation about them. This paper presents Memory Wrap, a module (i.e, a set of layers) that can be added to deep learning models to improve their performance and interpretability in settings where few data are available. Memory Wrap adopts a sparse content-attention mechanism between the input and some memories of past training samples. We show that adding Memory Wrap to standard deep neural networks improves their performance when they learn from a limited set of data, and allows them to reach comparable performance when they learn from the full dataset. We discuss how the analysis of its structure and content-attention weights helps to get insights about its decision process and makes their predictions more interpretable, compared to the same networks without Memory Wrap. We test our approach on image classification tasks using several networks on three different datasets, namely CIFAR10, SVHN, and CINIC10.<\/jats:p>","DOI":"10.1007\/s10489-022-03886-6","type":"journal-article","created":{"date-parts":[[2022,8,5]],"date-time":"2022-08-05T00:02:21Z","timestamp":1659657741000},"page":"9115-9147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A self-interpretable module for deep image classification on small data"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4071-170X","authenticated-orcid":false,"given":"Biagio","family":"La Rosa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,5]]},"reference":[{"key":"3886_CR1","unstructured":"Adebayo J, Gilmer J, Muelly M, et al., et al. (2018) Sanity checks for saliency maps. In: Bengio S, Wallach H, Larochelle H (eds) Advances in neural information processing systems, Curran Associates, Inc, Vol 31"},{"key":"3886_CR2","unstructured":"Bahng H, Chun S, Yun S, et al. (2020) Learning de-biased representations with biased representations. In: III HD, Singh A (eds) Proceedings of the 37th international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v119\/bahng20a.html, vol 119. PMLR, pp 528\u2013539"},{"key":"3886_CR3","doi-asserted-by":"crossref","unstructured":"Barz B, Denzler J (2020) Deep learning on small datasets without pre-training using cosine loss. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","DOI":"10.1109\/WACV45572.2020.9093286"},{"key":"3886_CR4","doi-asserted-by":"publisher","first-page":"688969","DOI":"10.3389\/fdata.2021.688969","volume":"4","author":"V Belle","year":"2021","unstructured":"Belle V, Papantonis I (2021) Principles and practice of explainable machine learning. Front Big Data 4:688969. https:\/\/doi.org\/10.3389\/fdata.2021.688969","journal-title":"Front Big Data"},{"key":"3886_CR5","doi-asserted-by":"publisher","unstructured":"Bercea CI, Pauly O, Maier A, et al. (2019) SHAMANN: Shared memory augmented neural networks. In: Lecture Notes in Computer Science. https:\/\/doi.org\/10.1007\/978-3-030-20351-1_65. Springer International Publishing, Cham, pp 830\u2013841","DOI":"10.1007\/978-3-030-20351-1_65"},{"key":"3886_CR6","unstructured":"Bietti A, Mialon G, Chen D, et al. (2019) A kernel perspective for regularizing deep neural networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol 97. PMLR. https:\/\/proceedings.mlr.press\/v97\/bietti19a.html, pp 664\u2013674"},{"key":"3886_CR7","unstructured":"Blondel M, Martins A, Niculae V (2019) Learning classifiers with fenchel-young losses: generalized entropies, margins, and algorithms. In: Chaudhuri K, Sugiyama M (eds) Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol 89. PMLR, pp 606\u2013615"},{"key":"3886_CR8","doi-asserted-by":"crossref","unstructured":"Cai Q, Pan Y, Yao T, et al. (2018) Memory matching networks for one-shot image recognition. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp 4080\u20134088","DOI":"10.1109\/CVPR.2018.00429"},{"key":"3886_CR9","doi-asserted-by":"publisher","unstructured":"Carion N, Massa F, Synnaeve G, et al. (2020) End-to-end object detection with transformers. In: Computer Vision \u2013 ECCV 2020. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13. Springer International Publishing, Cham, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"3886_CR10","unstructured":"Chen C, Li O, Tao D, et al. (2019) This looks like that: Deep learning for interpretable image recognition. In: Wallach H, Larochelle H, Beygelzimer A, et al. (eds) Advances in Neural Information. https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/adf7ee2dcf142b0e11888e72b43fcb75-Paper.pdf. Accessed 1 Dec. 2021"},{"issue":"12","key":"3886_CR11","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1038\/s42256-020-00265-z","volume":"2","author":"Z Chen","year":"2020","unstructured":"Chen Z, Bei Y, Rudin C (2020) Concept whitening for interpretable image recognition. Nat Mach Intell 2(12):772\u2013782. 10.1038\/s42256-020-00265-z","journal-title":"Nat Mach Intell"},{"issue":"141","key":"3886_CR12","doi-asserted-by":"publisher","first-page":"20170","DOI":"10.1098\/rsif.2017.0387","volume":"15","author":"T Ching","year":"2018","unstructured":"Ching T, Himmelstein DS, Beaulieu-Jones BK, et al. (2018) Opportunities and obstacles for deep learning in biology and medicine. J R Soc Interf 15(141):20170\u2013387. https:\/\/doi.org\/10.1098\/rsif.2017.0387. https:\/\/royalsocietypublishing.org\/doi\/10.1098\/rsif.2017.0387","journal-title":"J R Soc Interf"},{"key":"3886_CR13","doi-asserted-by":"publisher","unstructured":"Correia GM, Niculae V, Martins AFT (2019) Adaptively sparse transformers. Assoc Comput Linguist. https:\/\/doi.org\/10.18653\/v1\/d19-1223","DOI":"10.18653\/v1\/d19-1223"},{"issue":"1","key":"3886_CR14","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13 (1):21\u201327. https:\/\/doi.org\/10.1109\/tit.1967.1053964","journal-title":"IEEE Trans Inf Theory"},{"key":"3886_CR15","doi-asserted-by":"publisher","unstructured":"Darlow L N, Crowley E J, Antoniou A, et al. (2018) Cinic-10 is not imagenet or cifar-10, University of Edinburgh, [dataset], Tech. rep. https:\/\/doi.org\/10.7488\/DS\/2448","DOI":"10.7488\/DS\/2448"},{"key":"3886_CR16","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.neucom.2021.09.012","volume":"466","author":"W Ding","year":"2021","unstructured":"Ding W, Ming Y, Wang Y K, et al. (2021) Memory augmented convolutional neural network and its application in bioimages. Neurocomputing 466:128\u2013138. https:\/\/doi.org\/10.1016\/j.neucom.2021.09.012","journal-title":"Neurocomputing"},{"key":"3886_CR17","unstructured":"Donahue J, Jia Y, Vinyals O et al (2014) Decaf: A deep convolutional activation feature for generic visual recognition. In: Xing EP, Jebara T (eds) Proceedings of the 31st international conference on machine learning, proceedings of machine learning research, vol 32. https:\/\/proceedings.mlr.press\/v32\/donahue14.html. PMLR, China, pp 647\u2013655"},{"key":"3886_CR18","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, et al. (2021) An image is worth 16x16 words: transformers for image recognition at scale. International Conference on Learning Representations"},{"issue":"2","key":"3886_CR19","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/s10994-019-05855-6","volume":"109","author":"JE van Engelen","year":"2019","unstructured":"van Engelen JE, Hoos HH (2019) A survey on semi-supervised learning. Mach Learn 109 (2):373\u2013440. https:\/\/doi.org\/10.1007\/s10994-019-05855-6","journal-title":"Mach Learn"},{"key":"3886_CR20","doi-asserted-by":"publisher","unstructured":"Feng L, Li Z, Kuang Z et al (2018) Extractive video summarizer with memory augmented neural networks Proceedings of the 26th ACM international conference on Multimedia. https:\/\/doi.org\/10.1145\/3240508.3240651. ACM, pp 976\u2013983","DOI":"10.1145\/3240508.3240651"},{"issue":"2","key":"3886_CR21","doi-asserted-by":"publisher","first-page":"509","DOI":"10.32604\/cmc.2019.05250","volume":"59","author":"P Fu","year":"2019","unstructured":"Fu P, Xu Q, Zhang J, et al. (2019) A noise-resistant superpixel segmentation algorithm for hyperspectral images. Comput Mater Contin 59(2):509\u2013515. https:\/\/doi.org\/10.32604\/cmc.2019.05250","journal-title":"Comput Mater Contin"},{"key":"3886_CR22","unstructured":"Goyal Y, Wu Z, Ernst J, et al. (2019) Counterfactual visual explanations. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, proceedings of machine learning research, vol 97. https:\/\/proceedings.mlr.press\/v97\/goyal19a.html. PMLR, pp 2376\u20132384"},{"issue":"7626","key":"3886_CR23","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nature20101","volume":"538","author":"A Graves","year":"2016","unstructured":"Graves A, Wayne G, Reynolds M, et al. (2016) Hybrid computing using a neural network with dynamic external memory. Nature 538(7626):471\u2013476. https:\/\/doi.org\/10.1038\/nature20101","journal-title":"Nature"},{"key":"3886_CR24","doi-asserted-by":"publisher","unstructured":"Gurumoorthy KS, Dhurandhar A, Cecchi G, et al. (2019) Efficient data representation by selecting prototypes with importance weights. In: 2019 IEEE International Conference on Data Mining (ICDM). https:\/\/doi.org\/10.1109\/icdm.2019.00036. IEEE","DOI":"10.1109\/icdm.2019.00036"},{"issue":"6","key":"3886_CR25","doi-asserted-by":"publisher","first-page":"1441","DOI":"10.32604\/iasc.2020.011988","volume":"26","author":"H Song","year":"2020","unstructured":"Song H, Yang W, Yuan H, Bufford H (2020) Deep 3d-multiscale densenet for hyperspectral image classification based on spatial-spectral information. Intell Autom Soft Comput 26(6):1441\u20131458. https:\/\/doi.org\/10.32604\/iasc.2020.011988","journal-title":"Intell Autom Soft Comput"},{"key":"3886_CR26","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3","key":"3886_CR27","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.1109\/TGRS.2017.2765364","volume":"56","author":"L He","year":"2018","unstructured":"He L, Li J, Liu C, et al. (2018) Recent advances on spectral\u2013spatial hyperspectral image classification: an overview and new guidelines. IEEE Trans Geosci Remote Sens 56(3):1579\u20131597. https:\/\/doi.org\/10.1109\/tgrs.2017.2765364","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"3886_CR28","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Maaten LVD, et al. (2017) Densely connected convolutional networks. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR). IEEE, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"issue":"4","key":"3886_CR29","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1109\/TSM.2020.3010984","volume":"33","author":"Y Hyun","year":"2020","unstructured":"Hyun Y, Kim H (2020) Memory-augmented convolutional neural networks with triplet loss for imbalanced wafer defect pattern classification. IEEE Trans Semicond Manuf 33(4):622\u2013634. https:\/\/doi.org\/10.1109\/tsm.2020.3010984","journal-title":"IEEE Trans Semicond Manuf"},{"key":"3886_CR30","doi-asserted-by":"crossref","unstructured":"Kang D, Kwon H, Min J, et al. (2021) Relational embedding for few-shot classification. In: Proceedings of the IEEE\/CVF international conference on Computer Vision (ICCV), pp 8822\u20138833","DOI":"10.1109\/ICCV48922.2021.00870"},{"key":"3886_CR31","doi-asserted-by":"crossref","unstructured":"Kenny EM, Keane MT (2019) Twin-systems to explain artificial neural networks using case-based reasoning: Comparative tests of feature-weighting methods in ANN-CBR twins for XAI. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence. International Joint Conferences on Artificial Intelligence Organization, pp 2708\u20132715","DOI":"10.24963\/ijcai.2019\/376"},{"key":"3886_CR32","doi-asserted-by":"publisher","first-page":"107,530","DOI":"10.1016\/j.knosys.2021.107530","volume":"233","author":"EM Kenny","year":"2021","unstructured":"Kenny EM, Keane MT (2021) Explaining deep learning using examples: Optimal feature weighting methods for twin systems using post-hoc, explanation-by-example in XAI. Knowl-Based Syst 233:107,530. https:\/\/doi.org\/10.1016\/j.knosys.2021.107530","journal-title":"Knowl-Based Syst"},{"key":"3886_CR33","unstructured":"Kim B, Khanna R, Koyejo OO, et al. (2016) Examples are not enough, learn to criticize! criticism for interpretability. In: Lee D, Sugiyama M, Luxburg U (eds) Advances in neural information processing systems, vol 29. Curran Associates, Inc"},{"key":"3886_CR34","doi-asserted-by":"crossref","unstructured":"Kobayashi T (2021) t-vmf similarity for regularizing in-class feature distribution. In: Proceedings of IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR46437.2021.00655"},{"key":"3886_CR35","unstructured":"Koh PW, Nguyen T, Tang YS, et al. (2020) Concept bottleneck models. In: III HD, Singh A (eds) Proceedings of the 37th international conference on machine learning, proceedings of machine learning research, vol 119. https:\/\/proceedings.mlr.press\/v119\/koh20a.html. PMLR, pp 5338\u20135348"},{"key":"3886_CR36","volume-title":"Learning multiple layers of features from tiny images","author":"A Krizhevsky","year":"2009","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. University of Toronto, [dataset], Tech. rep."},{"key":"3886_CR37","unstructured":"Kumar A, Irsoy O, Ondruska P, et al. (2016) Ask me anything: Dynamic memory networks for natural language processing. In: Proceedings of the 33rd international conference on international conference on machine learning, ICML\u201916, vol 48. https:\/\/www.JMLR.org, pp 1378\u20131387"},{"key":"3886_CR38","doi-asserted-by":"crossref","unstructured":"La Rosa B, Capobianco R, Nardi D (2020) Explainable inference on sequential data via memory-tracking. In: Proceedings of the twenty-ninth international joint conference on artificial intelligence. International joint conferences on artificial intelligence organization, pp 2006\u20132013","DOI":"10.24963\/ijcai.2020\/278"},{"key":"3886_CR39","doi-asserted-by":"publisher","unstructured":"Laugel T, Lesot MJ, Marsala C et al (2018) Comparison-based inverse classification for interpretability in machine learning. In: Communications in computer and information science. https:\/\/doi.org\/10.1007\/978-3-319-91473-2_9. Springer International Publishing, Cham, pp 100\u2013111","DOI":"10.1007\/978-3-319-91473-2_9"},{"issue":"11","key":"3886_CR40","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. (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"3886_CR41","doi-asserted-by":"crossref","unstructured":"Lezama J, Qiu Q, Mus\u00e9 P, et al. (2018) Ol\u00c9: orthogonal low-rank embedding - a plug and play geometric loss for deep learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00846"},{"issue":"4","key":"3886_CR42","doi-asserted-by":"publisher","first-page":"841","DOI":"10.32604\/iasc.2020.010118","volume":"26","author":"H Li","year":"2020","unstructured":"Li H, Zeng W, Xiao G, et al. (2020) The instance-aware automatic image colorization based on deep convolutional neural network. Intell Autom Soft Comput 26(4):841\u2013846. https:\/\/doi.org\/10.32604\/iasc.2020.010118","journal-title":"Intell Autom Soft Comput"},{"key":"3886_CR43","doi-asserted-by":"crossref","unstructured":"Li L, Wang B, Verma M et al (2021) Scouter: Slot attention-based classifier for explainable image recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 1046\u20131055","DOI":"10.1109\/ICCV48922.2021.00108"},{"key":"3886_CR44","doi-asserted-by":"crossref","unstructured":"Li O, Liu H, Chen C et al (2018a) Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Proceedings of the AAAI conference on artificial intelligence. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/11771. Accessed 10 Dec. 2021. AAAI Press, USA","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"3886_CR45","doi-asserted-by":"crossref","unstructured":"Li O, Liu H, Chen C, et al. (2018b) Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Proceedings of the thirty-second AAAI conference on artificial intelligence and thirtieth innovative applications of artificial intelligence conference and eighth AAAI symposium on educational advances in artificial intelligence. AAAI\u201918\/IAAI\u201918\/EAAI\u201918. AAAI Press, USA","DOI":"10.1609\/aaai.v32i1.11771"},{"issue":"6","key":"3886_CR46","doi-asserted-by":"publisher","first-page":"e","DOI":"10.1002\/widm.1264","volume":"8","author":"Y Li","year":"2018","unstructured":"Li Y, Zhang H, Xue X, et al. (2018c) Deep learning for remote sensing image classification: a survey. WIREs Data Min Knowl Discov 8(6):e\u20131264. https:\/\/doi.org\/10.1002\/widm.1264","journal-title":"WIREs Data Min Knowl Discov"},{"issue":"3","key":"3886_CR47","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","volume":"16","author":"ZC Lipton","year":"2018","unstructured":"Lipton Z C (2018) The mythos of model interpretability: In machine learning, the concept of interpretability is both important and slippery. Queue 16(3):31\u201357","journal-title":"Queue"},{"key":"3886_CR48","doi-asserted-by":"publisher","unstructured":"Liu J, Ye J (2009) Efficient euclidean projections in linear time. In: Proceedings of the 26th Annual International Conference on Machine Learning - ICML \u201909. https:\/\/doi.org\/10.1145\/1553374.1553459. ACM Press","DOI":"10.1145\/1553374.1553459"},{"key":"3886_CR49","doi-asserted-by":"crossref","unstructured":"Liu S, Kailkhura B, Loveland D, et al. (2019) Generative counterfactual introspection for explainable deep learning. In: 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp 1\u20135","DOI":"10.1109\/GlobalSIP45357.2019.8969491"},{"key":"3886_CR50","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/978-3-030-86520-7_40","volume-title":"Interpretable counterfactual explanations guided by prototypes","author":"AV Looveren","year":"2021","unstructured":"Looveren AV, Klaise J (2021) Interpretable counterfactual explanations guided by prototypes. Springer International Publishing, Cham, pp 650\u2013665. https:\/\/doi.org\/10.1007\/978-3-030-86520-7_40"},{"key":"3886_CR51","doi-asserted-by":"crossref","unstructured":"Ma C, Shen C, Dick A, et al. (2018) Visual question answering with memory-augmented networks. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition. IEEE, pp 6975\u20136984","DOI":"10.1109\/CVPR.2018.00729"},{"key":"3886_CR52","doi-asserted-by":"publisher","unstructured":"Malaviya C, Ferreira P, Martins AFT (2018) Sparse and constrained attention for neural machine translation. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 2: Short Papers). https:\/\/doi.org\/10.18653\/v1\/p18-2059. Association for Computational Linguistics","DOI":"10.18653\/v1\/p18-2059"},{"key":"3886_CR53","unstructured":"Martins A, Astudillo R (2016a) From softmax to sparsemax: A sparse model of attention and multi-label classification. In: Balcan MF, Weinberger KQ (eds) Proceedings of the 33rd international conference on machine learning, proceedings of machine learning research, vol 48. PMLR, New York. USA, New York, pp 1614\u20131623"},{"key":"3886_CR54","unstructured":"Martins AFT, Astudillo RF (2016b) From softmax to sparsemax: a sparse model of attention and multi-label classification. In: Proceedings of the 33rd international conference on international conference on machine learning - Volume 48. JMLR.org, ICML\u201916, pp 1614\u20131623"},{"key":"3886_CR55","doi-asserted-by":"publisher","unstructured":"Miranda E, Aryuni M, Irwansyah E (2016) A survey of medical image classification techniques. In: 2016 International Conference on Information Management and Technology (ICIMTech). https:\/\/doi.org\/10.1109\/ICIMTech.2016.7930302, pp 56\u201361","DOI":"10.1109\/ICIMTech.2016.7930302"},{"key":"3886_CR56","doi-asserted-by":"publisher","unstructured":"Mothilal RK, Sharma A, Tan C (2020) Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness Accountability, and Transparency. https:\/\/doi.org\/10.1145\/3351095.3372850. ACM","DOI":"10.1145\/3351095.3372850"},{"issue":"4","key":"3886_CR57","doi-asserted-by":"publisher","first-page":"3825","DOI":"10.1007\/s10489-021-02619-5","volume":"52","author":"D Muthusamy","year":"2021","unstructured":"Muthusamy D, Rakkimuthu P (2021) Steepest deep bipolar cascade correlation for finger-vein verification. Appl Intell 52(4):3825\u20133845. https:\/\/doi.org\/10.1007\/s10489-021-02619-5","journal-title":"Appl Intell"},{"key":"3886_CR58","unstructured":"Netzer Y, Wang T, Coates A, et al. (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"3886_CR59","unstructured":"phi Nguyen A, Mart\u00ednez MR (2020) On quantitative aspects of model interpretability. https:\/\/arxiv.org\/abs\/2007.07584"},{"issue":"2","key":"3886_CR60","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s10462-005-4609-5","volume":"24","author":"C Nugent","year":"2005","unstructured":"Nugent C, Cunningham P (2005) A case-based explanation system for black-box systems. Artif Intell Rev 24(2):163\u2013178. https:\/\/doi.org\/10.1007\/s10462-005-4609-5","journal-title":"Artif Intell Rev"},{"key":"3886_CR61","unstructured":"Papernot N, McDaniel P (2018) Deep k-nearest neighbors: towards confident, interpretable and robust deep learning. https:\/\/arxiv.org\/abs\/1803.04765"},{"key":"3886_CR62","unstructured":"Rdusseeun L, Kaufman P (1987) Clustering by means of medoids. In: Proceedings of the statistical data analysis based on the L1 norm conference, Neuchatel, Switzerland, pp 405\u2013416"},{"issue":"3","key":"3886_CR63","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, et al. (2015) ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis (IJCV) 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis (IJCV)"},{"key":"3886_CR64","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, et al. (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3886_CR65","unstructured":"Santoro A, Bartunov S, Botvinick M, et al. (2016) Meta-learning with memory-augmented neural networks. In: Proceedings of machine learning research, vol 48. PMLR, pp 1842\u20131850"},{"key":"3886_CR66","doi-asserted-by":"publisher","first-page":"41,482","DOI":"10.1109\/ACCESS.2021.3064838","volume":"9","author":"G Singh","year":"2021","unstructured":"Singh G, Yow KC (2021) These do not look like those: An interpretable deep learning model for image recognition. IEEE Access 9:41,482\u201341,493. https:\/\/doi.org\/10.1109\/access.2021.3064838","journal-title":"IEEE Access"},{"key":"3886_CR67","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Proceedings of the 31st International conference on neural information processing systems. Curran Associates Inc., NIPS\u201917, pp 4080\u20134090"},{"issue":"2","key":"3886_CR68","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/ss\/1177012580","volume":"4","author":"SM Stigler","year":"1989","unstructured":"Stigler SM (1989) Francis galton\u2019s account of the invention of correlation. Stat Sci 4(2):73\u201379. https:\/\/doi.org\/10.1214\/ss\/1177012580https:\/\/doi.org\/10.1214\/ss\/1177012580","journal-title":"Stat Sci"},{"key":"3886_CR69","unstructured":"Sukhbaatar S, Szlam A, Weston J, et al. (2015) End-to-end memory networks. In: Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2. MIT Press, NIPS\u201915, pp 2440\u20132448"},{"key":"3886_CR70","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: Proceedings of the 34th international conference on machine learning - Volume 70. JMLR.org, ICML\u201917, pp 3319\u20133328"},{"key":"3886_CR71","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, et al. (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"3886_CR72","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, et al. (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"3886_CR73","doi-asserted-by":"publisher","unstructured":"Tan C, Sun F, Kong T, et al. (2018) A survey on deep transfer learning. In: Artificial Neural Networks and Machine Learning \u2013 ICANN 2018. https:\/\/doi.org\/10.1007\/978-3-030-01424-7_27. Springer International Publishing, Cham, pp 270\u2013279","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"3886_CR74","unstructured":"Tan M, Le Q (2019) EfficientNet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, proceedings of machine learning research, vol 97. PMLR, pp 6105\u20136114"},{"issue":"1-2","key":"3886_CR75","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/BF01016429","volume":"52","author":"C Tsallis","year":"1988","unstructured":"Tsallis C (1988) Possible generalization of boltzmann-gibbs statistics. J Stat Phys 52(1-2):479\u2013487. https:\/\/doi.org\/10.1007\/bf01016429https:\/\/doi.org\/10.1007\/bf01016429","journal-title":"J Stat Phys"},{"key":"3886_CR76","doi-asserted-by":"publisher","unstructured":"Ulicny M, Krylov VA, Dahyot R (2019) Harmonic networks with limited training samples. In: 2019 27th European Signal Processing Conference (EUSIPCO). https:\/\/doi.org\/10.23919\/eusipco.2019.8902831https:\/\/doi.org\/10.23919\/eusipco.2019.8902831. IEEE","DOI":"10.23919\/eusipco.2019.8902831 10.23919\/eusipco.2019.8902831"},{"key":"3886_CR77","doi-asserted-by":"publisher","unstructured":"Varshneya S, Ledent A, Vandermeulen RA, et al. (2021) Learning interpretable concept groups in CNNs. In: Proceedings of the thirtieth international joint conference on artificial intelligence. International joint conferences on artificial intelligence organization. https:\/\/doi.org\/10.24963\/ijcai.2021\/147","DOI":"10.24963\/ijcai.2021\/147"},{"key":"3886_CR78","unstructured":"Vinyals O, Blundell C, Lillicrap T, et al. (2016) Matching networks for one shot learning. In: Proceedings of the 30th international conference on neural information processing systems. Curran Associates Inc., NIPS\u201916, pp 3637\u20133645"},{"issue":"2","key":"3886_CR79","first-page":"841","volume":"31","author":"S Wachter","year":"2018","unstructured":"Wachter S, Mittelstadt B, Russell C (2018) Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Harv J Law Technol 31(2):841\u2013887","journal-title":"Harv J Law Technol"},{"key":"3886_CR80","doi-asserted-by":"crossref","unstructured":"Wang J, Liu H, Wang X, et al. (2021) Interpretable image recognition by constructing transparent embedding space. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 895\u2013904","DOI":"10.1109\/ICCV48922.2021.00093"},{"key":"3886_CR81","doi-asserted-by":"crossref","unstructured":"Wang P, Vasconcelos N (2020) Scout: Self-aware discriminant counterfactual explanations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00900"},{"issue":"3","key":"3886_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3386252","volume":"53","author":"Y Wang","year":"2020","unstructured":"Wang Y, Yao Q, Kwok JT, et al. (2020) Generalizing from a few examples. ACM Comput Surv 53(3):1\u201334. https:\/\/doi.org\/10.1145\/3386252https:\/\/doi.org\/10.1145\/3386252","journal-title":"ACM Comput Surv"},{"key":"3886_CR83","doi-asserted-by":"publisher","unstructured":"Wiegreffe S, Pinter Y (2019) Attention is not not explanation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th International joint conference on natural language processing (EMNLP-IJCNLP). https:\/\/doi.org\/10.18653\/v1\/d19-1002. Association for Computational Linguistics","DOI":"10.18653\/v1\/d19-1002"},{"issue":"1","key":"3886_CR84","doi-asserted-by":"publisher","first-page":"289","DOI":"10.32604\/cmc.2019.05990","volume":"61","author":"X Wu","year":"2019","unstructured":"Wu X, Luo C, Zhang Q, et al. (2019) Text detection and recognition for natural scene images using deep convolutional neural networks. Comput Mater Contin 61(1):289\u2013300. https:\/\/doi.org\/10.32604\/cmc.2019.05990","journal-title":"Comput Mater Contin"},{"key":"3886_CR85","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2021.3085672","volume":"60","author":"C Xing","year":"2021","unstructured":"Xing C, Wang M, Wang Z, et al. (2021) Diagonalized low-rank learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens 60:1\u201312. https:\/\/doi.org\/10.1109\/tgrs.2021.3085672","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"4","key":"3886_CR86","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.32604\/iasc.2020.012775","volume":"26","author":"U Yasmeen","year":"2020","unstructured":"Yasmeen U, Shah JH, Khan MA, et al. (2020) Text detection and classification from low quality natural images. Intell Autom Soft Comput 26(4):1251\u20131266. https:\/\/doi.org\/10.32604\/iasc.2020.012775https:\/\/doi.org\/10.32604\/iasc.2020.012775","journal-title":"Intell Autom Soft Comput"},{"key":"3886_CR87","doi-asserted-by":"publisher","unstructured":"Zagoruyko S, Komodakis N (2016) Wide residual networks. In: Proceedings of the British Machine Vision Conference 2016. https:\/\/doi.org\/10.5244\/c.30.87https:\/\/doi.org\/10.5244\/c.30.87. British Machine Vision Association","DOI":"10.5244\/c.30.87 10.5244\/c.30.87"},{"key":"3886_CR88","doi-asserted-by":"publisher","unstructured":"Zhang X, Zhou X, Lin M, et al. (2018) ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/cvpr.2018.00716https:\/\/doi.org\/10.1109\/cvpr.2018.00716. IEEE, pp 6848\u20136856","DOI":"10.1109\/cvpr.2018.00716 10.1109\/cvpr.2018.00716"},{"key":"3886_CR89","doi-asserted-by":"publisher","unstructured":"Zheng H, Fu J, Mei T, et al. (2017) Learning multi-attention convolutional neural network for fine-grained image recognition. In: 2017 IEEE International conference on computer vision (ICCV). IEEE. https:\/\/doi.org\/10.1109\/iccv.2017.557","DOI":"10.1109\/iccv.2017.557"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03886-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03886-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03886-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T09:19:28Z","timestamp":1682846368000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03886-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,5]]},"references-count":89,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["3886"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03886-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,5]]},"assertion":[{"value":"10 June 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}]}}