{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,7]],"date-time":"2023-05-07T04:23:24Z","timestamp":1683433404392},"reference-count":38,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2023,5,1]]},"DOI":"10.1587\/transinf.2022dlp0021","type":"journal-article","created":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T22:23:54Z","timestamp":1682893434000},"page":"735-745","source":"Crossref","is-referenced-by-count":0,"title":["Compression of Vehicle and Pedestrian Detection Network Based on YOLOv3 Model"],"prefix":"10.1587","volume":"E106.D","author":[{"given":"Lie","family":"GUO","sequence":"first","affiliation":[{"name":"School of Automotive Engineering, Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibing","family":"ZHAO","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering, Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiandong","family":"GAO","sequence":"additional","affiliation":[{"name":"School of Automotive Engineering, Dalian University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] X. Wu, D. Sahoo, and S.C.H. Hoi, \u201cRecent advances in deep learning for object detection,\u201d Neurocomputing, vol.396, pp.39-64, 2020. 10.1016\/j.neucom.2020.01.085","DOI":"10.1016\/j.neucom.2020.01.085"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] S. Zhai, S. Dong, D. Shang, and S. Wang, \u201cAn Improved Faster R-CNN Pedestrian Detection Algorithm Based on Feature Fusion and Context Analysis,\u201d IEEE Access, vol.8, pp.138117-138128, 2020. 10.1109\/access.2020.3012558","DOI":"10.1109\/ACCESS.2020.3012558"},{"key":"3","unstructured":"[3] T. Kang-Xia, P. Peng, and Q. Wen-Hu, \u201cFar-infrared pedestrian detection method based on YOLO model,\u201d Laser & Infrared, 2018."},{"key":"4","unstructured":"[4] L. Ken, H.E. Jiaojiao, Z. Yongping, et al., \u201cImproved YOLO vehicle detection algorithm,\u201d Modern Electronics Technique, 2019."},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] S. Ren, K. He, R. Girshick, and J. Sun, \u201cFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,\u201d IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.39, no.6, pp.1137-1149, 2017. 10.1109\/tpami.2016.2577031","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A.C. Berg, \u201cSSD: Single Shot MultiBox Detector,\u201d European Conference on Computer Vision, vol.9905, pp.21-37, Springer International Publishing, 2016. 10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"7","unstructured":"[7] J. Redmon and A. Farhadi, \u201cYOLOv3: An incremental improvement,\u201d arXiv e-prints, 2018."},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] H. Law and J. Deng, \u201cCornerNet: Detecting Objects as Paired Keypoints,\u201d International Journal of Computer Vision, vol.128, no.3, pp.642-656, 2020. 10.1007\/s11263-019-01204-1","DOI":"10.1007\/s11263-019-01204-1"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, and Q. Tian, \u201cCenterNet: Keypoint triplets for object detection,\u201d arXiv preprint arXiv:1904.08189v3, 2019.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"10","unstructured":"[10] M. Wistuba, A. Rawat, and T. Pedapati, \u201cA survey on neural architecture search,\u201d arXiv preprint arXiv:1905.01392, 2019."},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] X. Zhang, X. Zhou, M. Lin, and J. Sun, \u201cShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,\u201d 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.6848-6856, 2018. 10.1109\/cvpr.2018.00716","DOI":"10.1109\/CVPR.2018.00716"},{"key":"12","unstructured":"[12] F.N. Iandola, S. Han, M.W. Moskewicz, et al., \u201cSqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size,\u201d 2016."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] F. Chollet, \u201cXception: Deep learning with depthwise separable convolutions,\u201d arXiv e-prints, 2016.","DOI":"10.1109\/CVPR.2017.195"},{"key":"14","doi-asserted-by":"crossref","unstructured":"[14] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, \u201cMobilenetv2: Inverted residuals and linear bottlenecks,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.4510-4520, 2018. 10.1109\/cvpr.2018.00474","DOI":"10.1109\/CVPR.2018.00474"},{"key":"15","unstructured":"[15] M. Tan and Q.V. Le, \u201cMixConv: Mixed depthwise convolutional kernels,\u201d arXiv, 2019."},{"key":"16","unstructured":"[16] M. Tan and Q.V. Le, \u201cEfficientNet: Rethinking model scaling for convolutional neural networks,\u201d 2019."},{"key":"17","unstructured":"[17] S. Han, H. Mao, and W.J. Dally, \u201cDeep compression: Compressing deep neural networks with pruning,\u201d Trained Quantization and Huffman Coding, ICLR, 2016."},{"key":"18","unstructured":"[18] H. Li, A. Kadav, I. Durdanovic, et al., \u201cPruning filters for efficient ConvNets,\u201d 2016."},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan, and C. Zhang, \u201cLearning efficient convolutional networks through network slimming,\u201d Proc. IEEE International Conference on Computer Vision, pp.2755-2763, 2017. 10.1109\/iccv.2017.298","DOI":"10.1109\/ICCV.2017.298"},{"key":"20","unstructured":"[20] S. Ioffe and C. Szegedy, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d 2015."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] P. Zhang, Y. Zhong, and X. Li, \u201cSlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications,\u201d 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp.37-45, 2019. 10.1109\/iccvw.2019.00011","DOI":"10.1109\/ICCVW.2019.00011"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] Y. He, X. Zhang, and J. Sun, \u201cChannel Pruning for Accelerating Very Deep Neural Networks,\u201d Proc. IEEE International Conference on Computer Vision, pp.1398-1406, 2017. 10.1109\/iccv.2017.155","DOI":"10.1109\/ICCV.2017.155"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] Y. He, P. Liu, Z. Wang, Z. Hu, and Y. Yang, \u201cFilter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration,\u201d 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.4335-4344, 2019. 10.1109\/cvpr.2019.00447","DOI":"10.1109\/CVPR.2019.00447"},{"key":"24","doi-asserted-by":"publisher","unstructured":"[24] Y. Wang, X. Zhang, L. Xie, J. Zhou, H. Su, B. Zhang, and X. Hu, \u201cPruning from Scratch,\u201d Proc. AAAI Conference on Artificial Intelligence, vol.34, no.7, pp.12273-12280, 2020. 10.1609\/aaai.v34i07.6910","DOI":"10.1609\/aaai.v34i07.6910"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] J. Chen, Z. Zhu, C. Li, and Y. Zhao, \u201cSelf-Adaptive Network Pruning,\u201d Neural Information Processing, Lecture Notes in Computer Science, vol.11953, pp.175-186, Springer International Publishing, Cham, 2019. 10.1007\/978-3-030-36708-4_15","DOI":"10.1007\/978-3-030-36708-4_15"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] N. Liu, X. Ma, Z. Xu, Y. Wang, J. Tang, and J. Ye, \u201cAutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates,\u201d Proc. AAAI Conference on Artificial Intelligence, vol.34, no.4, pp.4876-4883, 2020. 10.1609\/aaai.v34i04.5924","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] S. Roy, P. Panda, G. Srinivasan, and A. Raghunathan, \u201cPruning Filters while Training for Efficiently Optimizing Deep Learning Networks,\u201d 2020 International Joint Conference on Neural Networks (IJCNN), pp.1-7, 2020. 10.1109\/ijcnn48605.2020.9207588","DOI":"10.1109\/IJCNN48605.2020.9207588"},{"key":"28","doi-asserted-by":"publisher","unstructured":"[28] B. Liu, Q. Wu, Y. Zhang, and Q. Cao, \u201cExploiting the Relationship between Pruning Ratio and Compression Effect for Neural Network Model Based on TensorFlow,\u201d Security and Communication Networks, vol.2020, pp.1-8, 2020. 10.1155\/2020\/5218612","DOI":"10.1155\/2020\/5218612"},{"key":"29","doi-asserted-by":"publisher","unstructured":"[29] J. Cheng, J. Wu, C. Leng, Y. Wang, and Q. Hu, \u201cQuantized CNN: A Unified Approach to Accelerate and Compress Convolutional Networks,\u201d IEEE Trans. Neural Netw. & Learning Systems, vol.29, no.10, pp.4730-4743, 2018. 10.1109\/tnnls.2017.2774288","DOI":"10.1109\/TNNLS.2017.2774288"},{"key":"30","unstructured":"[30] R. Banner, Y. Nahshan, E. Hoffer, et al., \u201cPost-training 4-bit quantization of convolution networks for rapid-deployment,\u201d 2018."},{"key":"31","unstructured":"[31] M. Courbariaux, Y. Bengio, and J.P. David, \u201cBinaryconnect: Training deep neural networks with binary weights during propagations,\u201d Advances in Neural Information Processing Systems, pp.3123-3131, 2015."},{"key":"32","doi-asserted-by":"crossref","unstructured":"[32] M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, \u201cXNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks,\u201d Computer Vision-ECCV 2016, Lecture Notes in Computer Science, vol.9908, pp.525-542, Springer International Publishing, Cham, 2016. 10.1007\/978-3-319-46493-0_32","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"33","unstructured":"[33] I. Hubara, M. Courbariaux, D. Soudry, et al., \u201cQuantized neural networks: Training neural networks with low precision weights and activations,\u201d Journal of Machine Learning Research, vol.18, 2016."},{"key":"34","unstructured":"[34] F. Yu, W. Xian, Y. Chen, et al., \u201cBdd100k: A diverse driving video database with scalable annotation tooling,\u201d arXiv preprint arXiv:1805.04687, 2018."},{"key":"35","doi-asserted-by":"crossref","unstructured":"[35] A. Geiger, P. Lenz, and R. Urtasun, \u201cAre we ready for autonomous driving? The KITTI vision benchmark suite,\u201d 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp.3354-3361, 2012. 10.1109\/cvpr.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[36] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, \u201cThe Cityscapes Dataset for Semantic Urban Scene Understanding,\u201d 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.3213-3223, 2016. 10.1109\/cvpr.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"key":"37","doi-asserted-by":"crossref","unstructured":"[37] X. Huang, X. Cheng, Q. Geng, B. Cao, D. Zhou, P. Wang, Y. Lin, and R. Yang, \u201cThe ApolloScape dataset for autonomous driving,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp.954-960, 2018. 10.1109\/cvprw.2018.00141","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"38","doi-asserted-by":"publisher","unstructured":"[38] K. Oksuz, B.C. Cam, S. Kalkan, and E. Akbas, \u201cImbalance Problems in Object Detection: A Review,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol.43, no.10, pp.3388-3415, 2021. 10.1109\/tpami.2020.2981890","DOI":"10.1109\/TPAMI.2020.2981890"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/5\/E106.D_2022DLP0021\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T04:16:56Z","timestamp":1683346616000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E106.D\/5\/E106.D_2022DLP0021\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,1]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2022dlp0021","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,1]]},"article-number":"2022DLP0021"}}