{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:38:51Z","timestamp":1760150331483,"version":"build-2065373602"},"reference-count":49,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176206","HTHZQSWS-KCCYB-2023040"],"award-info":[{"award-number":["62176206","HTHZQSWS-KCCYB-2023040"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Park of Hetao Shenzhen\u2013Hong Kong Science and Technology Innovation Cooperation Zone Program","award":["62176206","HTHZQSWS-KCCYB-2023040"],"award-info":[{"award-number":["62176206","HTHZQSWS-KCCYB-2023040"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Artificial intelligence is changing and influencing our world. As one of the main algorithms in the field of artificial intelligence, convolutional neural networks (CNNs) have developed rapidly in recent years. Especially after the emergence of NASNet, CNNs have gradually pushed the idea of AutoML to the public\u2019s attention, and large numbers of new structures designed by automatic searches are appearing. These networks are usually based on reinforcement learning and evolutionary learning algorithms. However, sometimes, the blocks of these networks are complex, and there is no small model for simpler tasks. Therefore, this paper proposes POSS-CNN aiming at target recognition and detection, which employs a multi-branch CNN structure with PSNC and a method of automatic parallel selection for super parameters based on a multi-branch CNN structure. Moreover, POSS-CNN can be broken up. By choosing a single branch or the combination of two branches as the \u201cbenchmark\u201d, as well as the overall POSS-CNN, we can achieve seven models with different precision and operations. The test accuracy of POSS-CNN for a recognition task tested on a CIFAR10 dataset can reach 86.4%, which is equivalent to AlexNet and VggNet, but the operation and parameters of the whole model in this paper are 45.9% and 45.8% of AlexNet, and 29.5% and 29.4% of VggNet. The mAP of POSS-CNN for a detection task tested on the LSVH dataset is 45.8, inferior to the 62.3 of YOLOv3. However, compared with YOLOv3, the operation and parameters of the model in this paper are reduced by 57.4% and 15.6%, respectively. After being accelerated by WRA, POSS-CNN for a detection task tested on an LSVH dataset can achieve 27 fps, and the energy efficiency is 0.42 J\/f, which is 5 times and 96.6 times better than GPU 2080Ti in performance and energy efficiency, respectively.<\/jats:p>","DOI":"10.3390\/info14110604","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T11:25:31Z","timestamp":1699356331000},"page":"604","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["POSS-CNN: An Automatically Generated Convolutional Neural Network with Precision and Operation Separable Structure Aiming at Target Recognition and Detection"],"prefix":"10.3390","volume":"14","author":[{"given":"Jia","family":"Hou","sequence":"first","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwei","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishuo","family":"Meng","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cimang","family":"Lu","sequence":"additional","affiliation":[{"name":"Shenzhen Xinrai Sinovoice Technology Co., Ltd., Shenzhen 518000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8221-7670","authenticated-orcid":false,"given":"Chen","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Microelectronics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18\u201323). Learning Transferable Architectures for Separable Image Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref_2","unstructured":"Larsson, G., Maire, M., and Shakhnarovich, G. (2017). FractalNet: Ultra-Deep Neural Networks without Residuals. International Conference on Neural Information. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4341","DOI":"10.1109\/TIP.2023.3297408","article-title":"Centralized Feature Pyramid for Object Detection","volume":"32","author":"Quan","year":"2023","journal-title":"IEEE Trans. Image Process."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Pan, J., Li, Z., Wei, Y., Chen, Z., Nong, Y., Zhou, B., Huan, W., Zou, J., Pan, Z., and Liu, W. (2023, January 26\u201328). FEDNet: A real-time deep-learning framework for object detection. Proceedings of the 2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China.","DOI":"10.1109\/ICETCI57876.2023.10176539"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"82613","DOI":"10.1109\/ACCESS.2023.3302279","article-title":"Multi-Branch Cascade Receptive Field Residual Network","volume":"11","author":"Zhang","year":"2023","journal-title":"IEEE Access"},{"key":"ref_6","unstructured":"Tan, M., and Le, Q.V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv."},{"key":"ref_7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image is Worth 16\u00d76 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_8","unstructured":"Brock, A., De, S., Smith, S.L., and Simonyan, K. (2021). High-Performance Large-Scale Image Recognition Without Normalization. arXiv."},{"key":"ref_9","first-page":"4780","article-title":"Regularized evolution for image classifier architecture search","volume":"33","author":"Real","year":"2019","journal-title":"Conf. Artif. Intell. (AAAI)"},{"key":"ref_10","unstructured":"Kang, M.-G., Kim, H.-H., and Kang, D.-J. (2018, January 17\u201320). Finding a High Accuracy Neural Network for the Welding Defects Classification Using Efficient Neural Architecture Search via Parameter Sharing. Proceedings of the International Conference on Control, Automation and Systems (ICCAS), PyeongChang, Republic of Korea."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhao, H., Yan, K., and Cao, M. (2023, January 21\u201323). Multi-branch Attention Fusion Network for Aspect Sentiment Classification. Proceedings of the 2023 8th International Conference on Intelligent Computing and Signal Processing (ICSP), Xi\u2019an, China.","DOI":"10.1109\/ICSP58490.2023.10248925"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Talemi, N.A., Kashiani, H., Malakshan, S.R., and Saadabadi, M.S.E. (2023, January 8\u201311). AAFACE: Attribute-Aware Attentional Network for Face Recognition. Proceedings of the 2023 IEEE International Conference on Image Processing (ICIP), Kuala Lumpur, Malaysia.","DOI":"10.1109\/ICIP49359.2023.10222666"},{"key":"ref_13","first-page":"1","article-title":"DBGNet: Dual-Branch Gate-Aware Network for Infrared Small Target Detection","volume":"61","author":"Chi","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","unstructured":"Luo, R., Tian, F., Qin, T., and Lin, T.-Y. (2018). Neural Architecture Optimization. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_17","unstructured":"Canny, J., Zhao, H., Jaros, B., Chen, Y., and Mao, J. (November, January 29). Machine learning at the limit. Proceedings of the IEEE International Conference on Big Data, Santa Clara, CA, USA."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1109\/TCSI.2019.2960841","article-title":"Deep In-Memory Architectures for Machine Learning Accuracy Versus Efficiency Trade-Offs","volume":"67","author":"Kang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"IEEE"},{"key":"ref_20","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2012","journal-title":"IEEE Adv. Neural Inf. Process. Syst."},{"key":"ref_21","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2016, January 27\u201330). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23\u201328). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Redmon, J., and Farhadi, A. (2017, January 21\u201326). Yolo9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref_29","unstructured":"Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"L\u00e9vesque, J.C., Gagn\u00e9, C., and Sabourin, R. (2016, January 25\u201329). Bayesian Hyperparameter Optimization for Ensemble Learning. Proceedings of the Conference on Uncertainty in Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v29i1.9354"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/TNNLS.2018.2881143","article-title":"A particle swarm optimization based flexible convolutional autoencoder for image classification","volume":"30","author":"Sun","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fielding, B., Lawrence, T., and Zhang, L. (2019, January 14\u201319). Evolving and Ensembling Deep CNN Architectures for Image Classification. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.","DOI":"10.1109\/IJCNN.2019.8852369"},{"key":"ref_33","unstructured":"Wang, B., Sun, Y., Xue, B., and Zhang, M. (2018). Australasian Joint Conference on Artificial Intelligence, Springer."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/j.ijleo.2018.07.044","article-title":"Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm","volume":"172","author":"Lee","year":"2018","journal-title":"Optik"},{"key":"ref_35","unstructured":"Baker, B., Gupta, O., Naik, N., and Raskar, R. (2016). Designing neural network architectures using reinforcement learning. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Neary, P. (2018, January 2\u20137). Automatic hyperparameter tuning in deep convolutional neural networks using asynchronous reinforcement learning. Proceedings of the 2018 IEEE International Conference on Cognitive Computing (ICCC), San Francisco, CA, USA.","DOI":"10.1109\/ICCC.2018.00017"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., and Reed, S. (2015, January 7\u201312). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_38","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, C., Zoph, B., Neumann, M., Shlens, J., Hua, W., Li, L.J., Li, F.F., Yuille, A., Huang, J., and Murphy, K. (2017). Progressive Neural Architecture Search. arXiv.","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Yan, J., Wu, W., Shao, J., and Liu, C.L. (2018, January 18\u201323). Practical Block-wise Neural Network Architecture Generation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00257"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18\u201323). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","article-title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks","volume":"52","author":"Chen","year":"2017","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_44","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"Ioffe","year":"2015","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Ioffe, S., Vanhoucke, V., and Alemi, A. (2017, January 4\u20139). Inception-v4, inception-resnet and the impact of residual connections on learning. Proceedings of the Conference on Artificial Intelligence (AAAI), San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"2150022","DOI":"10.1142\/S0218126621500225","article-title":"UL-CNN: An Ultra-Lightweight Convolutional Neural Network aiming at Flash-based Computing-In-Memory Architecture for Pedestrian Recognition","volume":"30","author":"Yang","year":"2021","journal-title":"J. Circuits Syst. Comput. (JCSC)"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1109\/TITS.2018.2838132","article-title":"SINet: A Scale-Insensitive Convolutional Neural Network for Fast Vehicle Detection","volume":"20","author":"Hu","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"3480","DOI":"10.1109\/TCSI.2019.2928682","article-title":"WRA: A 2.2-to-6.3 TOPS Highly Unified Dynamically Reconfigurable Accelerator Using a Novel Winograd Decomposition Algorithm for Convolutional Neural Networks","volume":"66","author":"Yang","year":"2019","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.1109\/TCSI.2020.2985727","article-title":"A Stride-based Convolution Decomposition Method to Stretch CNN Acceleration Algorithms for Efficient and Flexible Hardware Implementation","volume":"67","author":"Yang","year":"2020","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/14\/11\/604\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:18:59Z","timestamp":1760131139000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/14\/11\/604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":49,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["info14110604"],"URL":"https:\/\/doi.org\/10.3390\/info14110604","relation":{},"ISSN":["2078-2489"],"issn-type":[{"type":"electronic","value":"2078-2489"}],"subject":[],"published":{"date-parts":[[2023,11,7]]}}}