{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T04:21:59Z","timestamp":1773116519205,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3093541","type":"journal-article","created":{"date-parts":[[2021,6,30]],"date-time":"2021-06-30T19:43:54Z","timestamp":1625082234000},"page":"93871-93891","source":"Crossref","is-referenced-by-count":6,"title":["CMNN: Coupled Modular Neural Network"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2483-577X","authenticated-orcid":false,"given":"Md Intisar","family":"Chowdhury","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3101-749X","authenticated-orcid":false,"given":"Qiangfu","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2044-0671","authenticated-orcid":false,"given":"Kai","family":"Su","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4663-6739","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","year":"2021","journal-title":"Tiny-Image-Net Benchmarks"},{"key":"ref72","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref71","article-title":"DenseNet models for tiny ImageNet classification","author":"abai","year":"2019","journal-title":"arXiv 1904 10429"},{"key":"ref70","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","author":"huang","year":"2018","journal-title":"arXiv 1811 06965"},{"key":"ref76","article-title":"MixMo: Mixing multiple inputs for multiple outputs via deep subnetworks","author":"rame","year":"2021","journal-title":"arXiv 2103 06132"},{"key":"ref74","article-title":"Tiny imagenet challenge","author":"wu","year":"2017"},{"key":"ref39","article-title":"Efficient neural architecture search via parameter sharing","author":"pham","year":"2018","journal-title":"arXiv 1802 03268"},{"key":"ref75","first-page":"7","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"le","year":"2015"},{"key":"ref38","article-title":"Simple and efficient architecture search for convolutional neural networks","author":"elsken","year":"2017","journal-title":"Arxiv 1711 04528"},{"key":"ref33","first-page":"598","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"Large-scale evolution of image classifiers","author":"real","year":"2017","journal-title":"arXiv 1703 01041"},{"key":"ref31","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"arXiv 1905 11946"},{"key":"ref30","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2016","journal-title":"arXiv 1611 01578"},{"key":"ref37","article-title":"A survey on evolutionary neural architecture search","author":"liu","year":"2020","journal-title":"arXiv 2008 10937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.09.017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/29.45535"},{"key":"ref60","article-title":"SUGAR: Subgraph neural network with reinforcement pooling and self-supervised mutual information mechanism","author":"sun","year":"2021","journal-title":"arXiv 2101 08170"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00843"},{"key":"ref61","article-title":"Local critic training of deep neural networks","author":"lee","year":"2018","journal-title":"arXiv 1805 01128"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01201-8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref64","year":"2020","journal-title":"PyTorch"},{"key":"ref27","first-page":"10727","article-title":"DropBlock: A regularization method for convolutional networks","author":"ghiasi","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref66","first-page":"1","article-title":"Comparison between block-wise detection and a modular selective approach","author":"wang","year":"2020","journal-title":"Proc 11th Int Conf Awareness Sci Technol (iCAST)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref67","year":"2020","journal-title":"CIFAR-10\/100"},{"key":"ref68","article-title":"A downsampled variant of ImageNet as an alternative to the CIFAR datasets","author":"chrabaszcz","year":"2017","journal-title":"arXiv 1707 08819"},{"key":"ref69","article-title":"Big transfer (BiT): General visual representation learning","author":"kolesnikov","year":"2019","journal-title":"arXiv 1912 11370"},{"key":"ref2","first-page":"566","article-title":"CNN for handwritten Arabic digits recognition based on LeNet-5","author":"el-sawy","year":"2016","journal-title":"Proc Int Conf Adv Intell Syst Informat"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref25","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv 1503 02531"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref59","first-page":"8017","article-title":"Subgraph neural networks","volume":"33","author":"alsentzer","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5987"},{"key":"ref57","article-title":"Anytime inference with distilled hierarchical neural ensembles","author":"ruiz","year":"2020","journal-title":"arXiv 2003 01474"},{"key":"ref56","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"arXiv 1608 03983"},{"key":"ref55","article-title":"Snapshot ensembles: Train 1, get M for free","author":"huang","year":"2017","journal-title":"arXiv 1704 00109"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICAwST.2019.8923334"},{"key":"ref53","article-title":"Why m heads are better than one: Training a diverse ensemble of deep networks","author":"lee","year":"2015","journal-title":"arXiv 1511 06314"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9473(01)00065-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref11","article-title":"FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation","author":"wu","year":"2019","journal-title":"arXiv 1903 11816"},{"key":"ref40","article-title":"SMASH: One-shot model architecture search through HyperNetworks","author":"brock","year":"2017","journal-title":"Arxiv 1708 05344"},{"key":"ref12","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref16","article-title":"U-GAT-IT: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation","author":"kim","year":"2019","journal-title":"arXiv 1907 10830"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-61068-4_7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90014-7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.10.092"},{"key":"ref4","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref6","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref7","first-page":"21","article-title":"SSD: Single shot MultiBox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref46","first-page":"7517","article-title":"Knowledge distillation by on-the-fly native ensemble","author":"lan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","article-title":"Large scale distributed neural network training through online distillation","author":"anil","year":"2018","journal-title":"arXiv 1804 03235"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1613\/jair.614"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1249"},{"key":"ref42","article-title":"Faster discovery of neural architectures by searching for paths in a large model","author":"pham","year":"2018","journal-title":"Proc Workshop Track 6th Int Conf Learn Represent"},{"key":"ref41","article-title":"Neural architecture transfer","author":"lu","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015432"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/DASC-PICom-CBDCom-CyberSciTech49142.2020.00032"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09468686.pdf?arnumber=9468686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:56:50Z","timestamp":1639771010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9468686\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3093541","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}