{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:34:34Z","timestamp":1782405274348,"version":"3.54.5"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T00:00:00Z","timestamp":1600819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T00:00:00Z","timestamp":1600819200000},"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":["J Cloud Comp"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The image classification based on cloud computing suffers from difficult deployment as the network depth and data volume increase. Due to the depth of the model and the convolution process of each layer will produce a great amount of calculation, the GPU and storage performance of the device are extremely demanding, and the GPU and storage devices equipped on the embedded and mobile terminals cannot support large models. So it is necessary to compress the model so that the model can be deployed on these devices. Meanwhile, traditional compression based methods often miss many global features during the compression process, resulting in low classification accuracy. To solve the problem, this paper proposes a lightweight neural network model based on dilated convolution and depthwise separable convolution with twenty-nine layers for image classification. The proposed model employs the dilated convolution to expand the receptive field during the convolution process while maintaining the number of convolution parameters, which can extract more high-level global semantic features to improve the classification accuracy. Also, the depthwise separable convolution is applied to reduce the network parameters and computational complexity in convolution operations, which reduces the size of the network. The proposed model introduces three hyperparameters: width multiplier, image resolution, and dilated rate, to compress the network on the premise of ensuring accuracy. The experimental results show that compared with GoogleNet, the network proposed in this paper improves the classification accuracy by nearly 1%, and the number of parameters is reduced by 3.7 million.<\/jats:p>","DOI":"10.1186\/s13677-020-00203-9","type":"journal-article","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T11:03:39Z","timestamp":1600859019000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Lightweight image classifier using dilated and depthwise separable convolutions"],"prefix":"10.1186","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4870-2971","authenticated-orcid":false,"given":"Wei","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaozheng","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,23]]},"reference":[{"key":"203_CR1","unstructured":"krizhevsky A, Sutskever I, Hinton G (2012) Imagenet classification with deep convolutional neural networks In: Advances in Neural Information Processing Systems, 1097\u20131105."},{"key":"203_CR2","first-page":"1","volume-title":"International Conference on Learning Representations","author":"K Simonyan","year":"2014","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition In: International Conference on Learning Representations, 1\u201314.. IEEE, USA."},{"key":"203_CR3","first-page":"1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"C Szegedy","year":"2015","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1\u201312.. IEEE, USA."},{"issue":"4","key":"203_CR4","doi-asserted-by":"publisher","first-page":"2622","DOI":"10.1109\/JIOT.2019.2944007","volume":"7","author":"X Xu","year":"2020","unstructured":"Xu X, He C, Xu Z, Qi L, Wan S, Bhuiyan M (2020) Joint optimization of offloading utility and privacy for edge computing enabled iot. IEEE Internet Things J 7(4):2622\u20132629. https:\/\/doi.org\/10.1109\/JIOT.2019.2944007.","journal-title":"IEEE Internet Things J"},{"key":"203_CR5","first-page":"630","volume-title":"European Conference on Computer Vision","author":"K He","year":"2016","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks In: European Conference on Computer Vision, 630\u2013645.. Springer, German."},{"key":"203_CR6","first-page":"1492","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"S Xie","year":"2017","unstructured":"Xie S, Girshick R, Doll\u00e1r P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networks In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1492\u20131500.. IEEE, USA."},{"issue":"12","key":"203_CR7","doi-asserted-by":"publisher","first-page":"1785","DOI":"10.1109\/TC.2019.2935042","volume":"68","author":"J Zhou","year":"2019","unstructured":"Zhou J, Hu X, Ma Y, Sun J, Wei T, Hu S (2019) Improving availability of multicore real-time systems suffering both permanent and transient faults. IEEE Trans Comput 68(12):1785\u20131801.","journal-title":"IEEE Trans Comput"},{"key":"203_CR8","first-page":"1","volume-title":"International Conference on Learning Representations","author":"F Iandola","year":"2017","unstructured":"Iandola F, Han S, Moskewicz M, Ashraf K, Dally W, Keutzer K (2017) Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 In: International Conference on Learning Representations, 1\u201313.. IEEE, USA."},{"key":"203_CR9","doi-asserted-by":"crossref","unstructured":"Zhou J, Sun J, Zhou X, Wei T, Chen M, Hu S, Hu X (2018) IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38(12):2215\u20132228.","DOI":"10.1109\/TCAD.2018.2883993"},{"key":"203_CR10","doi-asserted-by":"publisher","unstructured":"Xu X, Cai Q, Zhang G, Zhang J, Tian W, Zhang X, Liu A (2018) An incentive mechanism for crowdsourcing markets with social welfare maximization in cloud-edge computing. Concurrency Comput: Pract Experience:4961. https:\/\/doi.org\/10.1002\/cpe.4961.","DOI":"10.1002\/cpe.4961"},{"key":"203_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.is.2020.101522","volume":"92","author":"J Li","year":"2020","unstructured":"Li J, Cai T, Deng K, Wang X, Sellis T, Xia F (2020) Community-diversified influence maximization in social networks. Information Systems 92:1\u201312.","journal-title":"Information Systems"},{"issue":"4","key":"203_CR12","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TSC.2019.2963301","volume":"13","author":"J Zhou","year":"2020","unstructured":"Zhou J, Sun J, Cong P, Liu Z, Zhou X, Wei T, Hu S (2020) Security-critical energy-aware task scheduling for heterogeneous real-time mpsocs in iot. IEEE Trans Serv Comput 13(4):745\u2013758. https:\/\/doi.org\/10.1109\/TSC.2019.2963301.","journal-title":"IEEE Trans Serv Comput"},{"key":"203_CR13","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.tbs.2020.01.002","volume":"19","author":"Y Guo","year":"2020","unstructured":"Guo Y, Wang J, Peeta S, Anastasopoulos P (2020) Personal and societal impacts of motorcycle ban policy on motorcyclists\u2019 home-to-work morning commute in china. Travel Behav Soc 19:137\u2013150.","journal-title":"Travel Behav Soc"},{"key":"203_CR14","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.tbs.2019.12.007","volume":"19","author":"Y Guo","year":"2020","unstructured":"Guo Y, Peeta S (2020) Impacts of personalized accessibility information on residential location choice and travel behavior. Travel Behav Soc 19:99\u2013111.","journal-title":"Travel Behav Soc"},{"issue":"4","key":"203_CR15","doi-asserted-by":"publisher","first-page":"308","DOI":"10.26599\/BDMA.2018.9020008","volume":"1","author":"A Ramlatchan","year":"2018","unstructured":"Ramlatchan A, Yang M, Liu Q, Li M, Wang J, Li Y (2018) A survey of matrix completion methods for recommendation systems. Big Data Mining and Analytics 1(4):308\u2013323.","journal-title":"Big Data Mining and Analytics"},{"issue":"2","key":"203_CR16","doi-asserted-by":"publisher","first-page":"128","DOI":"10.26599\/BDMA.2018.9020012","volume":"1","author":"C Zhang","year":"2018","unstructured":"Zhang C, Yang M, Lv J, Yang W (2018) An improved hybrid collaborative filtering algorithm based on tags and time factor. Big Data Mining and Analytics 1(2):128\u2013136.","journal-title":"Big Data Mining and Analytics"},{"key":"203_CR17","first-page":"1","volume-title":"International Conference on Learning Representations","author":"S Han","year":"2016","unstructured":"Han S, Mao H, Dally W (2016) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding In: International Conference on Learning Representations, 1\u201314.. IEEE, USA."},{"key":"203_CR18","first-page":"1135","volume-title":"Advances in Neural Information Processing Systems","author":"S Han","year":"2015","unstructured":"Han S, Pool J, Tran J, Dally W (2015) Learning both weights and connections for efficient neural network In: Advances in Neural Information Processing Systems, 1135\u20131143.. Springer, German."},{"key":"203_CR19","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/945445.945450","volume-title":"Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles","author":"S Ghemawat","year":"2003","unstructured":"Ghemawat S, Gobioff H, Leung S-T (2003) The google file system In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles, 29\u201343.. IEEE, USA."},{"key":"203_CR20","first-page":"1251","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"F Chollet","year":"2017","unstructured":"Chollet F (2017) Xception: Deep learning with depthwise separable convolutions In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1251\u20131258.. IEEE, USA."},{"key":"203_CR21","first-page":"1","volume-title":"International Conference on Learning Representations","author":"A Howard","year":"2017","unstructured":"Howard A, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications In: International Conference on Learning Representations, 1\u20139.. IEEE, USA."},{"issue":"1","key":"203_CR22","doi-asserted-by":"publisher","first-page":"48","DOI":"10.26599\/BDMA.2018.9020031","volume":"2","author":"S Kumar","year":"2018","unstructured":"Kumar S, Singh M (2018) Big data analytics for healthcare industry: impact, applications, and tools. Big Data Mining and Analytics 2(1):48\u201357.","journal-title":"Big Data Mining and Analytics"},{"issue":"2","key":"203_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1365815.1365816","volume":"26","author":"F Chang","year":"2008","unstructured":"Chang F, Dean J, Ghemawat S, Hsieh W, Wallach D, Burrows M, Chandra T, Fikes A, Gruber R (2008) Bigtable: A distributed storage system for structured data. ACM Trans Comput Syst (TOCS) 26(2):1\u201326.","journal-title":"ACM Trans Comput Syst (TOCS)"},{"issue":"3","key":"203_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.26599\/BDMA.2018.9020019","volume":"1","author":"Y Liu","year":"2018","unstructured":"Liu Y, Wang S, Khan M, He J (2018) A novel deep hybrid recommender system based on auto-encoder with neural collaborative filtering. Big Data Mining and Analytics 1(3):211\u2013221.","journal-title":"Big Data Mining and Analytics"},{"key":"203_CR25","doi-asserted-by":"publisher","unstructured":"Xu X, Mo R, Dai F, Lin W, Wan S, Dou W (2019) Dynamic resource provisioning with fault tolerance for data-intensive meteorological workflows in cloud. IEEE Trans Ind Inform. https:\/\/doi.org\/10.1109\/TII.2019.2959258.","DOI":"10.1109\/TII.2019.2959258"},{"issue":"1","key":"203_CR26","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) Mapreduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113.","journal-title":"Commun ACM"},{"key":"203_CR27","doi-asserted-by":"publisher","unstructured":"Xu X, Liu X, Xu Z, Wang C, Wan S, Yang X (2019) Joint optimization of resource utilization and load balance with privacy preservation for edge services in 5g networks. Mobile Netw Appl:1\u201312. https:\/\/doi.org\/10.1007\/s11036-019-01448-8.","DOI":"10.1007\/s11036-019-01448-8"},{"key":"203_CR28","first-page":"1","volume-title":"International Conference on Learning Representations","author":"F Yu","year":"2016","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions In: International Conference on Learning Representations, 1\u201313.. IEEE, USA."},{"key":"203_CR29","doi-asserted-by":"publisher","unstructured":"Wang L, Zhang X, Wang R, Yan C, Kou H, Qi L (2020) Diversified service recommendation with high accuracy and efficiency. Knowledge-Based Systems:106196. https:\/\/doi.org\/10.1016\/j.knosys.2020.106196.","DOI":"10.1016\/j.knosys.2020.106196"},{"key":"203_CR30","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1016\/j.future.2017.08.057","volume":"105","author":"X Xu","year":"2020","unstructured":"Xu X, Zhang X, Khan M, Dou W, Xue S, Yu S (2020) A balanced virtual machine scheduling method for energy-performance trade-offs in cyber-physical cloud systems. Futur Gener Comput Syst 105:789\u2013799.","journal-title":"Futur Gener Comput Syst"},{"key":"203_CR31","first-page":"7132","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Hu","year":"2018","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132\u20137141.. IEEE, USA."},{"key":"203_CR32","first-page":"6848","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"X Zhang","year":"2018","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6848\u20136856.. IEEE, USA."},{"key":"203_CR33","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.tbs.2018.07.003","volume":"13","author":"Y Guo","year":"2018","unstructured":"Guo Y, Wang J, Peeta S, Anastasopoulos P (2018) Impacts of internal migration, household registration system, and family planning policy on travel mode choice in china. Travel Behav Soc 13:128\u2013143.","journal-title":"Travel Behav Soc"},{"key":"203_CR34","doi-asserted-by":"publisher","unstructured":"Chen Y, Zhang N, Zhang Y, Chen X, Wu W, Shen X (2019) Energy efficient dynamic offloading in mobile edge computing for internet of things. Trans Cloud Comput. https:\/\/doi.org\/10.1109\/TCC.2019.2898657.","DOI":"10.1109\/TCC.2019.2898657"},{"key":"203_CR35","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.comcom.2020.04.018","volume":"157","author":"W Zhong","year":"2020","unstructured":"Zhong W, Yin X, Zhang X, Li S, Dou W, Wang R, Qi L (2020) Multi-dimensional quality-driven service recommendation with privacy-preservation in mobile edge environment. Comput Commun 157:116\u2013123. https:\/\/doi.org\/10.1016\/j.comcom.2020.04.018.","journal-title":"Comput Commun"},{"key":"203_CR36","doi-asserted-by":"publisher","unstructured":"Qi L, He Q, Chen F, Zhang X, Dou W, Ni Q (2020) Data-driven web apis recommendation for building web applications[j]. IEEE Trans Big Data. https:\/\/doi.org\/10.1109\/TBDATA.2020.2975587.","DOI":"10.1109\/TBDATA.2020.2975587"},{"key":"203_CR37","unstructured":"Han S, Mao H, Dally W (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149."},{"key":"203_CR38","first-page":"448","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","author":"S Ioffe","year":"2015","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift In: Proceedings of the 32nd International Conference on Machine Learning, 448\u2013456.. IEEE, USA."},{"key":"203_CR39","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Liu T, Wang X, Wang G, Cai J, et al (2018) Recent advances in convolutional neural networks. Pattern Recog 77:354\u2013377.","journal-title":"Pattern Recog"},{"key":"203_CR40","doi-asserted-by":"publisher","unstructured":"Liu H, Kou H, Yan C, Qi L (2020) Keywords-driven and popularity-aware paper recommendation based on undirected paper citation graph[j]. Complexity:1\u201315. https:\/\/doi.org\/10.1155\/2020\/2085638.","DOI":"10.1155\/2020\/2085638"},{"key":"203_CR41","first-page":"1","volume-title":"International Conference on Learning Representations","author":"D Kingma","year":"2015","unstructured":"Kingma D, Ba J (2015) Adam: A method for stochastic optimization In: International Conference on Learning Representations, 1\u201315.. IEEE, USA."},{"key":"203_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13638-019-1561-7","volume":"233","author":"H Liu","year":"2019","unstructured":"Liu H, Kou H, Yan C, Qi L (2019) Link prediction in paper citation network to construct paper correlation graph. EURASIP J Wirel Commun Netw 233:1\u201312. https:\/\/doi.org\/10.1186\/s13638-019-1561-7.","journal-title":"EURASIP J Wirel Commun Netw"},{"key":"203_CR43","first-page":"1","volume-title":"International Conference on Learning Representations","author":"H Hu","year":"2016","unstructured":"Hu H, Peng R, Tai Y-W, Tang C-K (2016) Network trimming: A data-driven neuron pruning approach towards efficient deep architectures In: International Conference on Learning Representations, 1\u20139.. IEEE, USA."},{"key":"203_CR44","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/2847263.2847265","volume-title":"Proceedings of the 2016 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","author":"J Qiu","year":"2016","unstructured":"Qiu J, Wang J, Yao S, Guo K, Li B, Zhou E, Yu J, Tang T, Xu N, Song S, et al. (2016) Going deeper with embedded fpga platform for convolutional neural network In: Proceedings of the 2016 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, 26\u201335.. IEEE, USA."},{"key":"203_CR45","first-page":"4820","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Wu","year":"2016","unstructured":"Wu J, Leng C, Wang Y, Hu Q, Cheng J (2016) Quantized convolutional neural networks for mobile devices In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4820\u20134828.. IEEE, USA."}],"container-title":["Journal of Cloud Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-020-00203-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13677-020-00203-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13677-020-00203-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T23:34:13Z","timestamp":1632353653000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofcloudcomputing.springeropen.com\/articles\/10.1186\/s13677-020-00203-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,23]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["203"],"URL":"https:\/\/doi.org\/10.1186\/s13677-020-00203-9","relation":{},"ISSN":["2192-113X"],"issn-type":[{"value":"2192-113X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,23]]},"assertion":[{"value":"15 February 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This manuscript has not been submitted to, nor is under review at, another journal or other publishing venue. The authors declare that they have no competing interests among authors.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"55"}}