{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T08:31:41Z","timestamp":1778056301997,"version":"3.51.4"},"reference-count":62,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,11,26]],"date-time":"2021-11-26T00:00:00Z","timestamp":1637884800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1A2C2010585"],"award-info":[{"award-number":["2021R1A2C2010585"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Information &amp; Communication Technology Planning &amp; Evaluation","award":["2021-0-00590"],"award-info":[{"award-number":["2021-0-00590"]}]},{"name":"BK21 FOUR Program","award":["BK21 FOUR Program"],"award-info":[{"award-number":["BK21 FOUR Program"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Robot vision is an essential research field that enables machines to perform various tasks by classifying\/detecting\/segmenting objects as humans do. The classification accuracy of machine learning algorithms already exceeds that of a well-trained human, and the results are rather saturated. Hence, in recent years, many studies have been conducted in the direction of reducing the weight of the model and applying it to mobile devices. For this purpose, we propose a multipath lightweight deep network using randomly selected dilated convolutions. The proposed network consists of two sets of multipath networks (minimum 2, maximum 8), where the output feature maps of one path are concatenated with the input feature maps of the other path so that the features are reusable and abundant. We also replace the 3\u00d73 standard convolution of each path with a randomly selected dilated convolution, which has the effect of increasing the receptive field. The proposed network lowers the number of floating point operations (FLOPs) and parameters by more than 50% and the classification error by 0.8% as compared to the state-of-the-art. We show that the proposed network is efficient.<\/jats:p>","DOI":"10.3390\/s21237862","type":"journal-article","created":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T01:45:02Z","timestamp":1638323102000},"page":"7862","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multipath Lightweight Deep Network Using Randomly Selected Dilated Convolution"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0117-2678","authenticated-orcid":false,"given":"Sangun","family":"Park","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6496-4189","authenticated-orcid":false,"given":"Dong Eui","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,26]]},"reference":[{"key":"ref_1","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_2","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_3","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_4","unstructured":"Dai, J., Li, Y., He, K., and Sun, J. (2016, January 5\u201310). R-fcn: Object detection via region-based fully convolutional networks. Proceedings of the Advances in Neural Information Processing Systems, Barcelona, Spain."},{"key":"ref_5","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_6","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Shen, Z., Liu, Z., Li, J., Jiang, Y.G., Chen, Y., and Xue, X. (2017, January 22\u201329). Dsod: Learning deeply supervised object detectors from scratch. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.212"},{"key":"ref_8","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":"Proc. IEEE"},{"key":"ref_9","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_11","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_12","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_13","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, S., Van der Maaten, L., and Weinberger, K.Q. (2018, January 18\u201322). Condensenet: An efficient densenet using learned group convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00291"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yang, L., Jiang, H., Cai, R., Wang, Y., Song, S., Huang, G., and Tian, Q. (2021, January 19\u201325). CondenseNet V2: Sparse Feature Reactivation for Deep Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00357"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., and Darrell, T. (2015, January 7\u201312). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhuge, M., Fan, D.P., Liu, N., Zhang, D., Xu, D., and Shao, L. (2021). Salient object detection via integrity learning. arXiv.","DOI":"10.1109\/TPAMI.2022.3179526"},{"key":"ref_21","unstructured":"Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (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_23","doi-asserted-by":"crossref","unstructured":"Han, D., Kim, J., and Kim, J. (2017, January 21\u201326). Deep pyramidal residual networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1007\/s10586-020-03144-9","article-title":"Towards an optimized distributed deep learning framework for a heterogeneous multi-GPU cluster","volume":"23","author":"Kim","year":"2020","journal-title":"Clust. Comput."},{"key":"ref_25","unstructured":"Sergeev, A., and Del Balso, M.H. (2018). fast and easy distributed deep learning in TensorFlow. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kim, S., Yu, G.I., Park, H., Cho, S., Jeong, E., Ha, H., Lee, S., Jeong, J.S., and Chun, B.G. (2019, January 25\u201328). Parallax: Sparsity-aware data parallel training of deep neural networks. Proceedings of the Fourteenth EuroSys Conference 2019, Dresden, Germany.","DOI":"10.1145\/3302424.3303957"},{"key":"ref_27","unstructured":"Krizhevsky, A. (2014). One weird trick for parallelizing convolutional neural networks. arXiv."},{"key":"ref_28","unstructured":"Jia, Z., Zaharia, M., and Aiken, A. (2018). Beyond data and model parallelism for deep neural networks. arXiv."},{"key":"ref_29","unstructured":"Park, J.H., Yun, G., Chang, M.Y., Nguyen, N.T., Lee, S., Choi, J., Noh, S.H., and Choi, Y.R. (2020, January 15\u201317). Hetpipe: Enabling large {DNN} training on (whimpy) heterogeneous {GPU} clusters through integration of pipelined model parallelism and data parallelism. Proceedings of the 2020 {USENIX} Annual Technical Conference ({USENIX}{ATC} 20), Boston, MA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Koliousis, A., Watcharapichat, P., Weidlich, M., Mai, L., Costa, P., and Pietzuch, P. (2019). CROSSBOW: Scaling deep learning with small batch sizes on multi-gpu servers. arXiv.","DOI":"10.14778\/3342263.3342276"},{"key":"ref_31","unstructured":"Han, S., Pool, J., Tran, J., and Dally, W.J. (2015). Learning both weights and connections for efficient neural networks. arXiv."},{"key":"ref_32","unstructured":"Chen, Y., Li, J., Xiao, H., Jin, X., Yan, S., and Feng, J. (2017). Dual path networks. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_34","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv."},{"key":"ref_35","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_36","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18\u201322). 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_37","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201322). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., and Sun, J. (2018, January 8\u201314). Shufflenet v2: Practical guidelines for efficient cnn architecture design. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (2019, January 27\u201328). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Zoph, B., Vasudevan, V., Shlens, J., and Le, Q.V. (2018, January 18\u201322). Learning transferable architectures for scalable image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref_41","unstructured":"Ioffe, S., and Szegedy, C. (2015, January 6\u201311). Batch normalization: Accelerating deep network training by reducing internal covariate shift. Proceedings of the International Conference on Machine Learning, Lille, France."},{"key":"ref_42","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201324). Rectified linear units improve restricted boltzmann machines. Proceedings of the ICML, Haifa, Israel."},{"key":"ref_43","unstructured":"Yu, F., and Koltun, V. (2015). Multi-scale context aggregation by dilated convolutions. arXiv."},{"key":"ref_44","unstructured":"Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, Available online: https:\/\/www.cs.toronto.edu\/kriz\/cifar.html."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). Imagenet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, Florida, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K.Q. (2016, January 11\u201314). Deep networks with stochastic depth. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref_47","unstructured":"Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., and Tu, Z. (2015, January 9\u201312). Deeply-supervised nets. Proceedings of the Artificial Intelligence and Statistics, PMLR, San Diego, CA, USA."},{"key":"ref_48","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., and Bengio, Y. (2014). Fitnets: Hints for thin deep nets. arXiv."},{"key":"ref_49","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv."},{"key":"ref_50","unstructured":"Srivastava, R.K., Greff, K., and Schmidhuber, J. (2015). Training very deep networks. arXiv."},{"key":"ref_51","unstructured":"Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv."},{"key":"ref_52","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Caterini, A.L., and Chang, D.E. (2018). Deep Neural Networks in a Mathematical Framework, Springer.","DOI":"10.1007\/978-3-319-75304-1"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Zagoruyko, S., and Komodakis, N. (2016). Wide residual networks. arXiv.","DOI":"10.5244\/C.30.87"},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., and He, K. (2017, January 21\u201326). Aggregated residual transformations for deep neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., and Sun, J. (2017, January 22\u201329). Channel pruning for accelerating very deep neural networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref_58","unstructured":"Li, H., Kadav, A., Durdanovic, I., Samet, H., and Graf, H.P. (2016). Pruning filters for efficient convnets. arXiv."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., and Zhang, C. (2017, January 22\u201329). Learning efficient convolutional networks through network slimming. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.298"},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Yu, R., Li, A., Chen, C.F., Lai, J.H., Morariu, V.I., Han, X., Gao, M., Lin, C.Y., and Davis, L.S. (2018, January 18\u201322). Nisp: Pruning networks using neuron importance score propagation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00958"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"He, Y., Liu, P., Wang, Z., Hu, Z., and Yang, Y. (2019, January 16\u201320). Filter pruning via geometric median for deep convolutional neural networks acceleration. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref_62","unstructured":"Howard, A., Zhmoginov, A., Chen, L.C., Sandler, M., and Zhu, M. (2018). Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7862\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:36:02Z","timestamp":1760168162000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/23\/7862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,26]]},"references-count":62,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["s21237862"],"URL":"https:\/\/doi.org\/10.3390\/s21237862","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,26]]}}}