{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T10:41:40Z","timestamp":1786272100686,"version":"build-2736575974"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T00:00:00Z","timestamp":1786233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T00:00:00Z","timestamp":1786233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62374049"],"award-info":[{"award-number":["62374049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-026-08752-7","type":"journal-article","created":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T09:49:27Z","timestamp":1786268967000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CDCA: a column-serial and dual-engine collaborative accelerator for depthwise separable convolution"],"prefix":"10.1007","volume":"82","author":[{"given":"Yiming","family":"Ouyang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhen","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,9]]},"reference":[{"issue":"6","key":"8752_CR1","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84\u201390. https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun ACM"},{"issue":"3","key":"8752_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/339751","volume":"13","author":"J Mu","year":"2020","unstructured":"Mu J, Zhang W, Liang H et al (2020) Optimizing opencl-based cnn design on fpga with comprehensive design space exploration and collaborative performance modeling. ACM Trans Reconfigurable Technol Syst (TRETS) 13(3):1\u201328. https:\/\/doi.org\/10.1145\/339751","journal-title":"ACM Trans Reconfigurable Technol Syst (TRETS)"},{"key":"8752_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107283","volume":"186","author":"C Fu","year":"2025","unstructured":"Fu C, Zhou T, Guo T et al (2025) Cnn-transformer and channel-spatial attention based network for hyperspectral image classification with few samples. Neural Netw 186:107283. https:\/\/doi.org\/10.1016\/j.neunet.2025.107283","journal-title":"Neural Netw"},{"key":"8752_CR4","doi-asserted-by":"publisher","unstructured":"Nguyen DT, Nguyen TN, Kim H, et\u00a0al (2019) A high-throughput and power-efficient fpga implementation of yolo cnn for object detection. IEEE Transactions on Very Large Scale Integration (VLSI) Systems 27(8):1861\u20131873. https:\/\/doi.org\/10.1109\/TVLSI.2019.2905242","DOI":"10.1109\/TVLSI.2019.2905242"},{"key":"8752_CR5","doi-asserted-by":"publisher","unstructured":"Choi J, Chun D, Kim H, et\u00a0al (2019) Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE\/CVF, pp 502\u2013511, https:\/\/doi.org\/10.1109\/ICCV.2019.00059","DOI":"10.1109\/ICCV.2019.00059"},{"key":"8752_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129826","volume":"634","author":"Z Yang","year":"2025","unstructured":"Yang Z, Tian Y, Wang L et al (2025) Enhancing generalization in camera trap image recognition: Fine-tuning visual language models. Neurocomputing 634:129826. https:\/\/doi.org\/10.1016\/j.neucom.2025.129826","journal-title":"Neurocomputing"},{"key":"8752_CR7","doi-asserted-by":"publisher","unstructured":"Liu S, Luk W (2019) Towards an efficient accelerator for dnn-based remote sensing image segmentation on fpgas. In: 2019 29th International Conference on Field Programmable Logic and Applications (FPL), IEEE, pp 187\u2013193, https:\/\/doi.org\/10.1109\/FPL.2019.00037","DOI":"10.1109\/FPL.2019.00037"},{"key":"8752_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.129690","volume":"630","author":"X Shu","year":"2025","unstructured":"Shu X, Li Z, Tian C et al (2025) An active learning model based on image similarity for skin lesion segmentation. Neurocomputing 630:129690. https:\/\/doi.org\/10.1016\/j.neucom.2025.129690","journal-title":"Neurocomputing"},{"key":"8752_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113005","volume":"311","author":"Z Xu","year":"2025","unstructured":"Xu Z, Wang H, Yang R et al (2025) Aggregated mutual learning between cnn and transformer for semi-supervised medical image segmentation. Knowl-Based Syst 311:113005. https:\/\/doi.org\/10.1016\/j.knosys.2025.113005","journal-title":"Knowl-Based Syst"},{"key":"8752_CR10","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.vlsi.2022.11.006","volume":"88","author":"J Shang","year":"2023","unstructured":"Shang J, Zhang K, Zhang Z et al (2023) A high-performance convolution block oriented accelerator for mbconv-based cnns. Integration 88:298\u2013312. https:\/\/doi.org\/10.1016\/j.vlsi.2022.11.006","journal-title":"Integration"},{"issue":"10","key":"8752_CR11","doi-asserted-by":"publisher","first-page":"7075","DOI":"10.1007\/s00371-024-03328-9","volume":"40","author":"M Rani","year":"2024","unstructured":"Rani M, Yadav J, Rathee N et al (2024) Optifusion: advancing visual intelligence in medical imaging through optimized cnn-tqwt fusion. Vis Comput 40(10):7075\u20137092. https:\/\/doi.org\/10.1007\/s00371-024-03328-9","journal-title":"Vis Comput"},{"key":"8752_CR12","doi-asserted-by":"publisher","unstructured":"Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 1251\u20131258, https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"8752_CR13","doi-asserted-by":"publisher","unstructured":"Chen Y, Lou J, Lanius C, et\u00a0al (2023) An energy-efficient and area-efficient depthwise separable convolution accelerator with minimal on-chip memory access. In: 2023 IFIP\/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC), IEEE, pp 1\u20136, https:\/\/doi.org\/10.1109\/VLSI-SoC57769.2023.10321918","DOI":"10.1109\/VLSI-SoC57769.2023.10321918"},{"key":"8752_CR14","doi-asserted-by":"publisher","unstructured":"Liu Z, Mao H, Wu CY, et\u00a0al (2022) A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE\/CVF, pp 11976\u201311986, https:\/\/doi.org\/10.1109\/CVPR52688.2022.01168","DOI":"10.1109\/CVPR52688.2022.01168"},{"issue":"3","key":"8752_CR15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MM.2020.2985963","volume":"40","author":"H Kwon","year":"2020","unstructured":"Kwon H, Chatarasi P, Sarkar V et al (2020) Maestro: a data-centric approach to understand reuse, performance, and hardware cost of dnn mappings. IEEE Micro 40(3):20\u201329. https:\/\/doi.org\/10.1109\/MM.2020.2985963","journal-title":"IEEE Micro"},{"issue":"8","key":"8752_CR16","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1109\/TCSI.2021.3078541","volume":"68","author":"B Li","year":"2021","unstructured":"Li B, Wang H, Zhang X et al (2021) Dynamic dataflow scheduling and computation mapping techniques for efficient depthwise separable convolution acceleration. IEEE Trans Circuits Syst I Regul Pap 68(8):3279\u20133292. https:\/\/doi.org\/10.1109\/TCSI.2021.3078541","journal-title":"IEEE Trans Circuits Syst I Regul Pap"},{"key":"8752_CR17","doi-asserted-by":"publisher","unstructured":"Wei G, Hou Y, Zhao Z, et\u00a0al (2018) Fpga-cloud architecture for cnn. In: 2018 24th Asia-Pacific Conference on Communications (APCC), IEEE, pp 7\u20138, https:\/\/doi.org\/10.1109\/APCC.2018.8633447","DOI":"10.1109\/APCC.2018.8633447"},{"key":"8752_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128444","volume":"290","author":"S Chatterjee","year":"2025","unstructured":"Chatterjee S, Pandit S, Das A (2025) Coupling of a lightweight model of reduced convolutional autoencoder with linear svm classifier to detect brain tumours on fpga. Expert Syst Appl 290:128444. https:\/\/doi.org\/10.1016\/j.eswa.2025.128444","journal-title":"Expert Syst Appl"},{"issue":"10","key":"8752_CR19","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1109\/TCSII.2018.2865896","volume":"65","author":"L Bai","year":"2018","unstructured":"Bai L, Zhao Y, Huang X (2018) A cnn accelerator on fpga using depthwise separable convolution. IEEE Trans Circuits Syst II Express Briefs 65(10):1415\u20131419. https:\/\/doi.org\/10.1109\/TCSII.2018.2865896","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"key":"8752_CR20","doi-asserted-by":"publisher","unstructured":"Liu Z, Liu Q, Yan S, et\u00a0al (2024) An efficient fpga-based depthwise separable convolutional neural network accelerator with hardware pruning. ACM Trans Reconfigurable Technol Syst 17(1):15:1\u201315:20. https:\/\/doi.org\/10.1145\/3615661","DOI":"10.1145\/3615661"},{"issue":"3","key":"8752_CR21","doi-asserted-by":"publisher","first-page":"281","DOI":"10.3390\/electronics8030281","volume":"8","author":"B Liu","year":"2019","unstructured":"Liu B, Zou D, Feng L et al (2019) An fpga-based cnn accelerator integrating depthwise separable convolution. Electronics 8(3):281. https:\/\/doi.org\/10.3390\/electronics8030281","journal-title":"Electronics"},{"issue":"12","key":"8752_CR22","doi-asserted-by":"publisher","first-page":"2708","DOI":"10.1109\/TC.2024.3449103","volume":"73","author":"M Park","year":"2024","unstructured":"Park M, Hwang S, Cho H (2024) Bird: Bi-directional input reuse dataflow for enhancing depthwise convolution performance on systolic arrays. IEEE Trans Comput 73(12):2708\u20132721. https:\/\/doi.org\/10.1109\/TC.2024.3449103","journal-title":"IEEE Trans Comput"},{"issue":"3","key":"8752_CR23","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.sysarc.2013.03.010","volume":"2","author":"JJ Shang","year":"2023","unstructured":"Shang JJ, Phipps N, Wey IC et al (2023) A-dscnn: depthwise separable convolutional neural network inference chip design using an approximate multiplier. Chips 2(3):159\u2013172. https:\/\/doi.org\/10.1016\/j.sysarc.2013.03.010","journal-title":"Chips"},{"key":"8752_CR24","doi-asserted-by":"publisher","unstructured":"Wu D, Zhang Y, Jia X, et\u00a0al (2019) A high-performance cnn processor based on fpga for mobilenets. In: 2019 29th International Conference on Field Programmable Logic and Applications (FPL), IEEE, pp 136\u2013143, https:\/\/doi.org\/10.1109\/FPL.2019.00030","DOI":"10.1109\/FPL.2019.00030"},{"key":"8752_CR25","doi-asserted-by":"publisher","unstructured":"Chen Y, Lou J, Wabnitz M, et\u00a0al (2024) Edea: efficient dual-engine accelerator for depthwise separable convolution with direct data transfer. In: 2024 IEEE 37th International System-on-Chip Conference (SOCC), IEEE, pp 1\u20136, https:\/\/doi.org\/10.1109\/SOCC62300.2024.10737823","DOI":"10.1109\/SOCC62300.2024.10737823"},{"key":"8752_CR26","doi-asserted-by":"publisher","unstructured":"Holly S, Wendt A, Lechner M, (2020) Profiling energy consumption of deep neural networks on nvidia jetson nano. In, (2020) 11th International Green and Sustainable Computing Workshops (IGSC). IEEE. https:\/\/doi.org\/10.1109\/IGSC51522.2020.9290876","DOI":"10.1109\/IGSC51522.2020.9290876"},{"key":"8752_CR27","doi-asserted-by":"publisher","unstructured":"Liu W, Li Y, Yang Y, et\u00a0al (2022) Design an efficient dnn inference framework with ps-pl synergies in fpga for edge computing. In: 2022 China Automation Congress (CAC), IEEE, pp 4186\u20134190, https:\/\/doi.org\/10.1109\/CAC57257.2022.10055627","DOI":"10.1109\/CAC57257.2022.10055627"},{"issue":"1","key":"8752_CR28","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11554-023-01520-z","volume":"21","author":"X Sang","year":"2024","unstructured":"Sang X, Ruan T, Li C et al (2024) A real-time and high-performance mobilenet accelerator based on adaptive dataflow scheduling for image classification. J Real-Time Image Proc 21(1):4. https:\/\/doi.org\/10.1007\/s11554-023-01520-z","journal-title":"J Real-Time Image Proc"},{"issue":"11","key":"8752_CR29","doi-asserted-by":"publisher","first-page":"4668","DOI":"10.1109\/TCSII.2024.3440884","volume":"71","author":"H Hong","year":"2024","unstructured":"Hong H, Choi D, Kim N et al (2024) Mobile-x: dedicated fpga implementation of the mobilenet accelerator optimizing depthwise separable convolution. IEEE Trans Circuits Syst II Express Briefs 71(11):4668\u20134672. https:\/\/doi.org\/10.1109\/TCSII.2024.3440884","journal-title":"IEEE Trans Circuits Syst II Express Briefs"},{"key":"8752_CR30","doi-asserted-by":"publisher","unstructured":"Qin W, Wu Z, Zhang J, et\u00a0al (2022) Design and optimization of mobilenet neural network acceleration system based on fpga. In: 2022 3rd International Conference on Electronics, Communications and Information Technology (CECIT), IEEE, pp 7\u201312, https:\/\/doi.org\/10.1109\/CECIT58139.2022.00010","DOI":"10.1109\/CECIT58139.2022.00010"},{"key":"8752_CR31","doi-asserted-by":"publisher","unstructured":"Lin Y, Li R, He W, et\u00a0al (2020) A high-speed low-cost cnn inference accelerator for depthwise separable convolution. In: 2020 IEEE International Conference on Integrated Circuits, Technologies and Applications (ICTA), IEEE, pp 63\u201364, https:\/\/doi.org\/10.1109\/ICTA50426.2020.9332057","DOI":"10.1109\/ICTA50426.2020.9332057"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08752-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-026-08752-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-026-08752-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,9]],"date-time":"2026-08-09T09:49:28Z","timestamp":1786268968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-026-08752-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,9]]},"references-count":31,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["8752"],"URL":"https:\/\/doi.org\/10.1007\/s11227-026-08752-7","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,9]]},"assertion":[{"value":"6 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"612"}}