{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:04:44Z","timestamp":1773486284254,"version":"3.50.1"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T00:00:00Z","timestamp":1766793600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T00:00:00Z","timestamp":1766793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10044-025-01559-x","type":"journal-article","created":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T00:28:12Z","timestamp":1766795292000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Partial derivative regularized knowledge transformation for deep neural networks generalization"],"prefix":"10.1007","volume":"29","author":[{"given":"Sajedeh","family":"Morabbi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2210-675X","authenticated-orcid":false,"given":"Hadi","family":"Soltanizadeh","sequence":"additional","affiliation":[]},{"given":"Saeed","family":"Mozaffari","sequence":"additional","affiliation":[]},{"given":"Mohammad Javad","family":"Fadaeieslam","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,27]]},"reference":[{"key":"1559_CR1","doi-asserted-by":"publisher","first-page":"36019","DOI":"10.1007\/s11042-023-15057-x","volume":"82","author":"X Xu","year":"2023","unstructured":"Xu X, Guo Y, Wang X (2023) Human pose estimation model based on DiracNets and integral pose regression. Multimed Tools Appl 82:36019\u201336039. https:\/\/doi.org\/10.1007\/s11042-023-15057-x","journal-title":"Multimed Tools Appl"},{"key":"1559_CR2","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1007\/s11277-021-09159-8","volume":"123","author":"A Jeya Christy","year":"2022","unstructured":"Jeya Christy A, Dhanalakshmi K (2022) Content-based image recognition and tagging by deep learning methods. Wirel Pers Commun 123:813\u2013838. https:\/\/doi.org\/10.1007\/s11277-021-09159-8","journal-title":"Wirel Pers Commun"},{"key":"1559_CR3","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1007\/s11277-018-5246-z","volume":"102","author":"F Cheng","year":"2018","unstructured":"Cheng F, Zhang H, Fan W, Harris B (2018) Image recognition technology based on deep learning. Wirel Pers Commun 102:1917\u20131933. https:\/\/doi.org\/10.1007\/s11277-018-5246-z","journal-title":"Wirel Pers Commun"},{"key":"1559_CR4","doi-asserted-by":"publisher","first-page":"23917","DOI":"10.1007\/s11042-022-14187-y","volume":"82","author":"C Termritthikun","year":"2023","unstructured":"Termritthikun C, Jamtsho Y, Muneesawang P et al (2023) Evolutionary neural architecture search based on efficient CNN models population for image classification. Multimed Tools Appl 82:23917\u201323943. https:\/\/doi.org\/10.1007\/s11042-022-14187-y","journal-title":"Multimed Tools Appl"},{"key":"1559_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01233-4_6","author":"AS Hashemi","year":"2022","unstructured":"Hashemi AS, B\u00e4r A, Mozaffari S, Fingscheidt T (2022) Improving transferability of\u00a0generated universal adversarial perturbations for\u00a0image classification and\u00a0segmentation. Deep Neural Networks Data Autom Driv. https:\/\/doi.org\/10.1007\/978-3-031-01233-4_6","journal-title":"Deep Neural Networks Data Autom Driv"},{"key":"1559_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12792-5","author":"P Cao","year":"2022","unstructured":"Cao P, Xie F, Zhang S et al (2022) Msanet: multi-scale attention networks for image classification. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-022-12792-5","journal-title":"Multimed Tools Appl"},{"key":"1559_CR7","doi-asserted-by":"publisher","first-page":"2823","DOI":"10.1007\/s11042-023-15089-3","volume":"83","author":"K Adu","year":"2024","unstructured":"Adu K, Walker J, Mensah PK et al (2024) Squeezecapsnet: enhancing capsule networks with squeezenet for holistic medical and complex images. Multimed Tools Appl 83:2823\u20132852. https:\/\/doi.org\/10.1007\/s11042-023-15089-3","journal-title":"Multimed Tools Appl"},{"key":"1559_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89010-0_4","author":"OA MontesinosL\u00f3pez","year":"2022","unstructured":"MontesinosL\u00f3pez OA, MontesinosL\u00f3pez A, Crossa J (2022) Overfitting, model tuning, and evaluation of prediction performance. Multivar Stat Mach Learn Methods Genomic Predict. https:\/\/doi.org\/10.1007\/978-3-030-89010-0_4","journal-title":"Multivar Stat Mach Learn Methods Genomic Predict"},{"key":"1559_CR9","doi-asserted-by":"publisher","first-page":"6676","DOI":"10.1007\/s11227-020-03525-2","volume":"77","author":"MF Tsai","year":"2021","unstructured":"Tsai MF, Tseng HJ (2021) Enhancing the identification accuracy of deep learning object detection using natural language processing. J Supercomput 77:6676\u20136691. https:\/\/doi.org\/10.1007\/s11227-020-03525-2","journal-title":"J Supercomput"},{"key":"1559_CR10","doi-asserted-by":"crossref","unstructured":"Ng AY (2004) Feature selection, L_1 vs. L_2 regularization, and rotational invairance. ICML \u201904 Proc 21st Int Conf Mach Learn 78","DOI":"10.1145\/1015330.1015435"},{"key":"1559_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118873","author":"M Yang","year":"2023","unstructured":"Yang M, Lim MK, Qu Y et al (2023) Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction. Expert Syst Appl. https:\/\/doi.org\/10.1016\/j.eswa.2022.118873","journal-title":"Expert Syst Appl"},{"key":"1559_CR12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.00554","author":"T Hoefler","year":"2021","unstructured":"Hoefler T, Alistarh D, Ben-Nun T et al (2021) Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. J Mach Learn Res. https:\/\/doi.org\/10.48550\/arXiv.2102.00554","journal-title":"J Mach Learn Res"},{"key":"1559_CR13","doi-asserted-by":"publisher","first-page":"22077","DOI":"10.1007\/s11042-020-10379-6","volume":"80","author":"AS Hashemi","year":"2021","unstructured":"Hashemi AS, Mozaffari S (2021) CNN adversarial attack mitigation using perturbed samples training. Multimed Tools Appl 80:22077\u201322095. https:\/\/doi.org\/10.1007\/s11042-020-10379-6","journal-title":"Multimed Tools Appl"},{"key":"1559_CR14","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/s11277-021-09152-1","volume":"123","author":"S Sharma","year":"2022","unstructured":"Sharma S, Singh S (2022) Recognition of Indian Sign Language (ISL) using deep learning model. Wirel Pers Commun 123:671\u2013692. https:\/\/doi.org\/10.1007\/s11277-021-09152-1","journal-title":"Wirel Pers Commun"},{"key":"1559_CR15","doi-asserted-by":"publisher","first-page":"9155","DOI":"10.1109\/CVPR.2019.00938","volume":"2019","author":"S Ahn","year":"2019","unstructured":"Ahn S, Hu SX, Damianou A et al (2019) Variational information distillation for knowledge transfer. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2019:9155\u20139163. https:\/\/doi.org\/10.1109\/CVPR.2019.00938","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"1559_CR16","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.compind.2019.02.003","volume":"108","author":"S Coulibaly","year":"2019","unstructured":"Coulibaly S, Kamsu-Foguem B, Kamissoko D, Traore D (2019) Deep neural networks with transfer learning in millet crop images. Comput Ind 108:115\u2013120. https:\/\/doi.org\/10.1016\/j.compind.2019.02.003","journal-title":"Comput Ind"},{"key":"1559_CR17","doi-asserted-by":"crossref","unstructured":"Morabbi S, Soltanizadeh H, Mozaffari S, et al (2024) Knowledge In Attention Assisstant for Improving Generalization in Deep Teacher-Student Models. Int J Model Simulation, [Under Rev]","DOI":"10.1080\/02286203.2024.2389562"},{"key":"1559_CR18","doi-asserted-by":"publisher","first-page":"20899","DOI":"10.1007\/s11227-023-05448-0","volume":"79","author":"S Morabbi","year":"2023","unstructured":"Morabbi S, Soltanizadeh H, Mozaffari S, Fadaeieslam MJ (2023) Improving generalization in deep neural network using knowledge transformation based on fisher criterion. J Supercomput 79:20899\u201320922. https:\/\/doi.org\/10.1007\/s11227-023-05448-0","journal-title":"J Supercomput"},{"key":"1559_CR19","unstructured":"Morabbi S, Soltanizadeh H, Mozaffari S, Fadaeieslam MJ (2024) Inner-Dual Soft Knowledge Distillation and Dual-Fisher for Improving Generalization in Deep Neural Network. Knowl Inf Syst [Under Rev]"},{"key":"1559_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05448-0","author":"S Morabbi","year":"2023","unstructured":"Morabbi S, Soltanizadeh H, Mozaffari S, Fadaeieslam MJ (2023) Improving generalization in deep neural network using knowledge transformation based on fisher criterion. J Supercomput. https:\/\/doi.org\/10.1007\/s11227-023-05448-0","journal-title":"J Supercomput"},{"key":"1559_CR21","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-3-031-01233-4","volume-title":"Deep neural networks and data for automated driving: robustness, uncertainty quantification, and insights towards safety","author":"T Fingscheidt","year":"2022","unstructured":"Fingscheidt T (2022) Deep neural networks and data for automated driving: robustness, uncertainty quantification, and insights towards safety. Springer Nature, Cham, pp 171\u2013196"},{"key":"1559_CR22","doi-asserted-by":"publisher","first-page":"25235","DOI":"10.1007\/s11042-023-14608-6","volume":"82","author":"S Jung","year":"2023","unstructured":"Jung S, Chung M, Shin YG (2023) Adversarial example detection by predicting adversarial noise in the frequency domain. Multimed Tools Appl 82:25235\u201325251. https:\/\/doi.org\/10.1007\/s11042-023-14608-6","journal-title":"Multimed Tools Appl"},{"key":"1559_CR23","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.cose.2019.06.012","volume":"86","author":"AS Hashemi","year":"2019","unstructured":"Hashemi AS, Mozaffari S (2019) Secure deep neural networks using adversarial image generation and training with Noise-GAN. Comput Secur 86:372\u2013387. https:\/\/doi.org\/10.1016\/j.cose.2019.06.012","journal-title":"Comput Secur"},{"key":"1559_CR24","first-page":"1","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. Sci Dep Univ Toronto, Toronto, pp 1\u201360"},{"key":"1559_CR25","doi-asserted-by":"crossref","unstructured":"Jia Deng, Wei Dong, Socher R, et al (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":"1559_CR26","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1007\/s11277-023-10463-8","volume":"131","author":"L Yao","year":"2023","unstructured":"Yao L, Zhao H (2023) Deep learning method of facial expression recognition based on Gabor filter bank combined with PCNN. Wirel Pers Commun 131:955\u2013971. https:\/\/doi.org\/10.1007\/s11277-023-10463-8","journal-title":"Wirel Pers Commun"},{"key":"1559_CR27","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s11277-022-09758-z","volume":"126","author":"B Mathivanan","year":"2022","unstructured":"Mathivanan B, Perumal P (2022) Gait recognition analysis for human identification analysis-a hybrid deep learning process. Wirel Pers Commun 126:555\u2013579. https:\/\/doi.org\/10.1007\/s11277-022-09758-z","journal-title":"Wirel Pers Commun"},{"key":"1559_CR28","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1007\/s11277-021-08525-w","volume":"120","author":"NS Khan","year":"2021","unstructured":"Khan NS, Ghani MS (2021) A survey of deep learning based models for human activity recognition. Wirel Pers Commun 120:1593\u20131635. https:\/\/doi.org\/10.1007\/s11277-021-08525-w","journal-title":"Wirel Pers Commun"},{"key":"1559_CR29","doi-asserted-by":"publisher","first-page":"159808","DOI":"10.1109\/ACCESS.2019.2950766","volume":"7","author":"Y Wang","year":"2019","unstructured":"Wang Y, Zhang S, Zhang C et al (2019) A low-complexity belief propagation based decoding scheme for polar codes-decodability detection and early stopping prediction. IEEE Access 7:159808\u2013159820. https:\/\/doi.org\/10.1109\/ACCESS.2019.2950766","journal-title":"IEEE Access"},{"key":"1559_CR30","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang C, Bengio S, Hardt M et al (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64:107\u2013115. https:\/\/doi.org\/10.1145\/3446776","journal-title":"Commun ACM"},{"key":"1559_CR31","doi-asserted-by":"publisher","unstructured":"Zhang W, Sun X, Li Y, et al (2022) A multi-task network with\u00a0weight decay skip connection training for\u00a0anomaly detection in\u00a0retinal fundus images. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 13432 LNCS:656\u2013666. https:\/\/doi.org\/10.1007\/978-3-031-16434-7_63","DOI":"10.1007\/978-3-031-16434-7_63"},{"key":"1559_CR32","doi-asserted-by":"publisher","first-page":"29887","DOI":"10.1007\/s11042-022-12058-0","volume":"81","author":"M Bentoumi","year":"2022","unstructured":"Bentoumi M, Daoud M, Benaouali M, Taleb Ahmed A (2022) Improvement of emotion recognition from facial images using deep learning and early stopping cross validation. Multimed Tools Appl 81:29887\u201329917. https:\/\/doi.org\/10.1007\/s11042-022-12058-0","journal-title":"Multimed Tools Appl"},{"key":"1559_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2021.111741","author":"Y Ren","year":"2022","unstructured":"Ren Y, Pan Y, Duan F (2022) Snr gain enhancement in a generalized matched filter using artificial optimal noise. Chaos Solitons Fractals. https:\/\/doi.org\/10.1016\/j.chaos.2021.111741","journal-title":"Chaos Solitons Fractals"},{"key":"1559_CR34","unstructured":"Hinton GE, Srivastava N, Krizhevsky A, et al (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv Prepr arXiv12070580"},{"key":"1559_CR35","doi-asserted-by":"publisher","unstructured":"Williams T, Li R (2021) Threshout regularization for deep neural networks. Conf Proc - IEEE SOUTHEASTCON 2021-March: https:\/\/doi.org\/10.1109\/SoutheastCon45413.2021.9401944","DOI":"10.1109\/SoutheastCon45413.2021.9401944"},{"key":"1559_CR36","unstructured":"Courville IG and YB and A (2016) Deep learning. Nature"},{"key":"1559_CR37","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-17394-3","author":"S Ben Hamida","year":"2023","unstructured":"Ben Hamida S, Mrabet H, Chaieb F, Jemai A (2023) Assessment of data augmentation, dropout with L2 regularization and differential privacy against membership inference attacks. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-023-17394-3","journal-title":"Multimed Tools Appl"},{"key":"1559_CR38","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1007\/s11277-018-5377-2","volume":"103","author":"Y Li","year":"2018","unstructured":"Li Y, Lu Z, Li J, Deng Y (2018) Improving deep learning feature with facial texture feature for face recognition. Wirel Pers Commun 103:1195\u20131206. https:\/\/doi.org\/10.1007\/s11277-018-5377-2","journal-title":"Wirel Pers Commun"},{"key":"1559_CR39","doi-asserted-by":"publisher","unstructured":"Ishii M, Sato A (2018) Layer-Wise Weight Decay for Deep Neural Networks. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 10749 LNCS:276\u2013289. https:\/\/doi.org\/10.1007\/978-3-319-75786-5_23","DOI":"10.1007\/978-3-319-75786-5_23"},{"key":"1559_CR40","unstructured":"Krueger D, Ballas N, Jastrzebski S, et al (2017) Deep nets don\u2019t learn via memorization. 5th Int Conf Learn Represent ICLR 2017 - Work Track Proc"},{"key":"1559_CR41","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1109\/TNN.2007.915114","volume":"19","author":"Y Liu","year":"2008","unstructured":"Liu Y, Starzyk JA, Zhu Z (2008) Optimized approximation algorithm in neural networks without overfitting. IEEE Trans Neural Netw 19:983\u2013995. https:\/\/doi.org\/10.1109\/TNN.2007.915114","journal-title":"IEEE Trans Neural Netw"},{"key":"1559_CR42","doi-asserted-by":"publisher","first-page":"2437","DOI":"10.1080\/15376494.2020.1864071","volume":"29","author":"S Mouloodi","year":"2022","unstructured":"Mouloodi S, Rahmanpanah H, Burvill C et al (2022) Experimental, regression learner, numerical, and artificial neural network analyses on a complex composite structure subjected to compression loading. Mech Adv Mater Struct 29:2437\u20132453. https:\/\/doi.org\/10.1080\/15376494.2020.1864071","journal-title":"Mech Adv Mater Struct"},{"key":"1559_CR43","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18221-z","author":"H Yang","year":"2024","unstructured":"Yang H, Yin H, Yang Z, Zhang Y (2024) JoCaD: a joint training method by combining consistency and diversity. Multimed Tools Appl. https:\/\/doi.org\/10.1007\/s11042-024-18221-z","journal-title":"Multimed Tools Appl"},{"key":"1559_CR44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00036","author":"X Liu","year":"2020","unstructured":"Liu X, Xiao T, Si S et al (2020) How does noise help robustness? Explanation and exploration under the neural SDE framework. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00036","journal-title":"Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit"},{"key":"1559_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.petrol.2019.106587","author":"DA Wood","year":"2020","unstructured":"Wood DA (2020) Predicting porosity, permeability and water saturation applying an optimized nearest-neighbour, machine-learning and data-mining network of well-log data. J Pet Sci Eng. https:\/\/doi.org\/10.1016\/j.petrol.2019.106587","journal-title":"J Pet Sci Eng"},{"key":"1559_CR46","doi-asserted-by":"publisher","first-page":"26581","DOI":"10.1007\/s11042-023-16603-3","volume":"83","author":"F Wang","year":"2024","unstructured":"Wang F, Ben K, Peng H, Yang M (2024) Neighbormix data augmentation for image recognition. Multimed Tools Appl 83:26581\u201326598. https:\/\/doi.org\/10.1007\/s11042-023-16603-3","journal-title":"Multimed Tools Appl"},{"key":"1559_CR47","unstructured":"Pang T, Xu K, Dong Y, et al (2019) Rethinking softmax cross-entropy loss for adversarial robustness"},{"key":"1559_CR48","unstructured":"Smith SL, Elsen E, De S (2020) On the generalization benefit of noise in stochastic gradient descent"},{"key":"1559_CR49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.03275","author":"SI Google","year":"2017","unstructured":"Google SI (2017) Batch renormalization: towards reducing minibatch dependence in batch-normalized models. Adv Neural Inf Process Syst. https:\/\/doi.org\/10.48550\/arXiv.1702.03275","journal-title":"Adv Neural Inf Process Syst"},{"key":"1559_CR50","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 et al (2019) L1 -norm batch normalization for efficient training of deep neural networks. IEEE Trans Neural Netw Learn Syst 30:2043\u20132051. https:\/\/doi.org\/10.1109\/TNNLS.2018.2876179","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1559_CR51","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1007\/978-3-030-32520-6_12","volume":"1069","author":"VI Avrutskiy","year":"2020","unstructured":"Avrutskiy VI (2020) Preventing overfitting by training derivatives. Adv Intell Syst Comput 1069:144\u2013163. https:\/\/doi.org\/10.1007\/978-3-030-32520-6_12","journal-title":"Adv Intell Syst Comput"},{"key":"1559_CR52","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107111","author":"F Daraee","year":"2021","unstructured":"Daraee F, Mozaffari S, Razavi SM (2021) Handwritten keyword spotting using deep neural networks and certainty prediction. Comput Electr Eng. https:\/\/doi.org\/10.1016\/j.compeleceng.2021.107111","journal-title":"Comput Electr Eng"},{"key":"1559_CR53","doi-asserted-by":"publisher","first-page":"6249","DOI":"10.1007\/s11042-023-15747-6","volume":"83","author":"IH Rather","year":"2024","unstructured":"Rather IH, Kumar S (2024) Generative adversarial network based synthetic data training model for lightweight convolutional neural networks. Multimed Tools Appl 83:6249\u20136271. https:\/\/doi.org\/10.1007\/s11042-023-15747-6","journal-title":"Multimed Tools Appl"},{"key":"1559_CR54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.pmcj.2019.04.004","volume":"57","author":"Y Chen","year":"2019","unstructured":"Chen Y, Wang J, Huang M, Yu H (2019) Cross-position activity recognition with stratified transfer learning. Pervasive Mob Comput 57:1\u201313. https:\/\/doi.org\/10.1016\/j.pmcj.2019.04.004","journal-title":"Pervasive Mob Comput"},{"key":"1559_CR55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-58347-1_9","author":"J Hoffman","year":"2017","unstructured":"Hoffman J, Tzeng E, Darrell T, Saenko K (2017) Simultaneous deep transfer across domains and tasks. Adv Comput Vis Pattern Recognit. https:\/\/doi.org\/10.1007\/978-3-319-58347-1_9","journal-title":"Adv Comput Vis Pattern Recognit"},{"key":"1559_CR56","unstructured":"Foret P, Kleiner A, Mobahi H, Neyshabur B (2021) Sharpness-Aware Minimization for Efficiently Improving Generalization. ICLR 2021 - 9th Int Conf Learn Represent"},{"key":"1559_CR57","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. 7th Int Conf Learn Represent ICLR 2019"},{"key":"1559_CR58","doi-asserted-by":"publisher","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) FaceNet: A unified embedding for face recognition and clustering. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 07\u201312-June. pp. 815\u2013823. https:\/\/doi.org\/10.1109\/CVPR.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"1559_CR59","doi-asserted-by":"publisher","unstructured":"Wieczorek M, Rychalska B, D\u0105browski J (2021) On the\u00a0Unreasonable Effectiveness of\u00a0Centroids in\u00a0Image Retrieval. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 13111 LNCS: pp. 212\u2013223. https:\/\/doi.org\/10.1007\/978-3-030-92273-3_18","DOI":"10.1007\/978-3-030-92273-3_18"},{"key":"1559_CR60","doi-asserted-by":"publisher","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S (2019) ArcFace: Additive angular margin loss for deep face recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2019-June. pp. 4685\u20134694. https:\/\/doi.org\/10.1109\/CVPR.2019.00482","DOI":"10.1109\/CVPR.2019.00482"},{"key":"1559_CR61","unstructured":"Simonyan Karen, Zisserman Andrew (2015) Very deep convolutional networks for large-scale image recognition. 3rd Int Conf Learn Represent ICLR 2015 - Conf Track Proc 14"},{"key":"1559_CR62","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2016-Decem. pp. 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"1559_CR63","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117473","author":"Y Zhang","year":"2022","unstructured":"Zhang Y, Liu W, Wang X, Shaheer MA (2022) A novel hierarchical hyper-parameter search algorithm based on greedy strategy for wind turbine fault diagnosis. Expert Syst Appl. https:\/\/doi.org\/10.1016\/j.eswa.2022.117473","journal-title":"Expert Syst Appl"},{"key":"1559_CR64","doi-asserted-by":"publisher","first-page":"15621","DOI":"10.1007\/s10489-022-04230-8","volume":"53","author":"OK Oyedotun","year":"2023","unstructured":"Oyedotun OK, Papadopoulos K, Aouada D (2023) A new perspective for understanding generalization gap of deep neural networks trained with large batch sizes. Appl Intell 53:15621\u201315637. https:\/\/doi.org\/10.1007\/s10489-022-04230-8","journal-title":"Appl Intell"},{"key":"1559_CR65","doi-asserted-by":"publisher","DOI":"10.1007\/s40687-022-00352-0","author":"B Wang","year":"2022","unstructured":"Wang B, Xia H, Nguyen T, Osher S (2022) How does momentum benefit deep neural networks architecture design? A few case studies. Res Math Sci. https:\/\/doi.org\/10.1007\/s40687-022-00352-0","journal-title":"Res Math Sci"},{"key":"1559_CR66","doi-asserted-by":"publisher","unstructured":"Wu Y, Liu L, Bae J, et al (2019) Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks. Proc - 2019 IEEE Int Conf Big Data, Big Data 2019. pp. 1971\u20131980. https:\/\/doi.org\/10.1109\/BigData47090.2019.9006104","DOI":"10.1109\/BigData47090.2019.9006104"},{"key":"1559_CR67","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12143106","author":"I Salehin","year":"2023","unstructured":"Salehin I, Kang DK (2023) A review on dropout regularization approaches for deep neural networks within the scholarly domain. Electronics. https:\/\/doi.org\/10.3390\/electronics12143106","journal-title":"Electronics"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01559-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10044-025-01559-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-025-01559-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T10:38:31Z","timestamp":1773484711000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10044-025-01559-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,27]]},"references-count":67,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["1559"],"URL":"https:\/\/doi.org\/10.1007\/s10044-025-01559-x","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,27]]},"assertion":[{"value":"16 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"12"}}