{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T01:48:07Z","timestamp":1783648087699,"version":"3.55.0"},"reference-count":46,"publisher":"National Library of Serbia","issue":"2","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ComSIS","COMPUT SCI INF SYST","COMPUT SCI INFORM SY","COMPUTER SCI INFORM","COMSIS J"],"published-print":{"date-parts":[[2023]]},"abstract":"<jats:p>Most research efforts on image classification so far have been focused on medium-scale datasets. In addition, there exist other problems, such as difficulty in feature extraction and small sample size. In order to address above difficulties, this paper proposes a multi-perspective convolutional neural network model, which contains channel attention module and spatial attention module. The proposed modules derive attention graphs from channel dimension and spatial dimension respectively, then the input features are selectively learned according to the importance of the features. We explain how the gain in storage can be traded against a loss in accuracy and\/or an increase in CPU cost. In addition, we give the interpretability of the model at multiple scales. Quantitative and qualitative experimental results demonstrate that the accuracy of our proposed model can be improved by up to 3.8% and outperforms the state-of-the-art methods.<\/jats:p>","DOI":"10.2298\/csis220714015w","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T08:28:09Z","timestamp":1677659289000},"page":"743-763","source":"Crossref","is-referenced-by-count":2,"title":["Large-scale image classification with multi-perspective deep transfer learning"],"prefix":"10.2298","volume":"20","author":[{"given":"Bin","family":"Wu","sequence":"first","affiliation":[{"name":"School of Internet of Things Engineering, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Ship Scientific Research Center, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1078","reference":[{"key":"ref1","unstructured":"Diba, A., Sharma, V.: Weakly super-vised cascaded convolutional networks. In: IEEE conference on computer vision and pattern recognition (CVPR). New York, NY, 5"},{"key":"ref2","doi-asserted-by":"crossref","unstructured":"Ren, S. H., He, K. M., Girshick, R.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Trans Pattern Analysis And Machine Intelligence, Vol. 39, 1137-1149. (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref3","unstructured":"Ross, G., Donahue, J., Darrell, T., Malik, J.: Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In: IEEE conference on computer vision and pattern recognition (CVPR), Columbus, Ohio, 580-587. (2014)"},{"key":"ref4","unstructured":"Chen, X., Li, M., Hsu, C. H.: DNNOff: Offloading DNN-based Intelligent IoT Applications in Mobile Edge Computing. IEEE Transactions on Industrial Informatics, 612-623. (2021)"},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"Chen, X., Chen, S. H., Ma, Y., Huang, G.: An Adaptive Offloading Framework for Android Applications in Mobile Edge Computing. SCIENCE CHINA Information Sciences, Vol. 62, No. 8, 821-832. (2019)","DOI":"10.1007\/s11432-018-9749-8"},{"key":"ref6","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, G., Liu, X. Z., Zhang, W., Mei, H.: Refactoring android Java code for on-demand computation offloading. ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications, 980-987. (2012)","DOI":"10.1145\/2384616.2384634"},{"key":"ref7","unstructured":"Chen, X., Hu, J., Chen, Z. Y., Lin, B., Min, G. Y.: A Reinforcement Learning Empowered Feedback Control System for Industrial Internet of Things. IEEE Transactions on Industrial Informatics, 1109-1124. (2021)"},{"key":"ref8","doi-asserted-by":"crossref","unstructured":"Lin, B., Huang, Y., Zhang, J. S., Hu, J., Li, J.: Cost-Driven Offloading for DNN-based Applications over Cloud, Edge and End Devices. IEEE Transactions on Industrial Informatics, Vol. 16, No. 8, 5456-5466. (2020)","DOI":"10.1109\/TII.2019.2961237"},{"key":"ref9","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, F., Zhang, J. S., Chen, J., Mauri, J. L.: A Time-driven Data Placement Strategy for a Scientific Workflow Combining Edge Computing and Cloud Computing. IEEE Transactions on Industrial Informatics, Vol. 15, No. 7, 4254-4265. (2019)","DOI":"10.1109\/TII.2019.2905659"},{"key":"ref10","doi-asserted-by":"crossref","unstructured":"Gong, C., Ding, Y., Han, B., Yang, J., Tao, D. C.: Class-Wise Denoising for Robust Learning under Label Noise. IEEE Transactions on Pattern Analysis and Machine Intelligence,12-28. (2022)","DOI":"10.1109\/TPAMI.2022.3178690"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Gong, C., Wang, Q. Z., Liu, T. L., Hu, J., Yang, J., Tao, D. C.: Instance-Dependent Positive and Unlabeled Learning with Labeling Bias Estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence,189-199. ( 2021)","DOI":"10.1109\/TPAMI.2021.3061456"},{"key":"ref12","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhu, F. N., Zhang, J. S., Chen, Z. Y., Min, J. Y.: Resource Allocation for Cloud-based Software Services Using Prediction-Enabled Feedback Control with Reinforcement Learning. IEEE Transactions on Cloud Computing, 111-125. (2022)","DOI":"10.1109\/TCC.2020.2992537"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Huang, G., Luo, C. R., Wu, K. D., Ma, Y., Zhang, Y.: Software-Defined Infrastructure for Decentralized Data Lifecycle Governance: Principled Design and Open Challenges. IEEE International Conference on Distributed Computing Systems, 236-252. (2019)","DOI":"10.1109\/ICDCS.2019.00166"},{"key":"ref14","unstructured":"Florian, S., Kalenichenko, D., Philbin, J. S.: FaceNet: A Unified Embedding for Face Recognition and Clustering. In: IEEE conference on computer vision and pattern recognition (CVPR), 815-823. (2015)"},{"key":"ref15","doi-asserted-by":"crossref","unstructured":"Leung, Y., Ji, N. N., Ma, J.: An integrated information fusion approach based on the theory of evidence and group decision-making, Information Fusion,Vol. 14, No. 4, 410-422. (2013)","DOI":"10.1016\/j.inffus.2012.08.002"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"Parkhi, O. M., Andrea, V., Andrew, Z.: Deep Face Recognition. In: British machine vision conference (BMVC), 110-119. (2015)","DOI":"10.5244\/C.29.41"},{"key":"ref17","unstructured":"Jamie, S., Andrew, F., Mat, C., Alex, K., Blake, N.: Real-Time Human Pose Recognition in Parts from Single Depth Images. In: IEEE conference on computer vision and pattern recognition (CVPR), 1297-1304. (2011)"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K. Y., Deng, J.: Stacked Hourglass Networks for Human Pose Estimation. In: Computer Vision-ECCV, 483-99. (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref19","doi-asserted-by":"crossref","unstructured":"Alex, K., Sutskever, I., Geoffrey, E., Hinton, J.: ImageNet Classification with Deep Convolutional Neural Networks. Communications of The ACM. Vol. 60, 84-90. (2017)","DOI":"10.1145\/3065386"},{"key":"ref20","unstructured":"Cires, A., Dan, U., Juergen, S.: MultiColumn Deep Neural Networks for Image Classification. In: IEEE conference on computer vision and pattern recognition (CVPR), 3642-3649. (2012) 131-5139. (2017)"},{"key":"ref21","unstructured":"Chen, S., Gong, C., Yang, J., Niu, G., Sugiyama, M.: Learning Contrastive Embedding in Low-Dimensional Space. Annual Conference on Neural Information Processing Systems. Berlin Heidelberg New York. (2022)"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Pentina, A., Sharmanska, V., Lampert, C. H.: Curriculum learning of multiple tasks. In Proceedings of the 28th IEEE Conference on Computer Vision and Pattern Recognition, 2547-2554. (2015)","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"Lin, L., Wang, K., Meng, D., Hu, J., Li, J.: Active Self-Paced Learning for Cost-Effective and Progressive Face Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7-19. (2017)","DOI":"10.1109\/TPAMI.2017.2652459"},{"key":"ref24","unstructured":"Holzinger, A., Biemann, C., Constantinos, S. P., Douglas, B.: What do we need to build explainable ai systems for the medical domain?, arXiv:1411.1784 (2017)"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Arrieta, A. B., Rodriguez, N. D., Ser, J. D., Bennetot, A., Herrera, F.: Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Information Fusion, vol. 58, 82-115, June (2020)","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref26","unstructured":"Xu, D., Yang, W., Xavier, A. P., Wang, X. J., Sebe, N.: Learning deep structured multi-scale features using attention-gated crfs for contour prediction. In NIPS, 3961-3970. (2017)"},{"key":"ref27","doi-asserted-by":"crossref","unstructured":"Sachan, S., Yang, J., Xu, D. L., Benavides, D., Li, Y.: An explainable AI decision-support-system to automate loan underwriting. Expert Systems with Applications, Vol. 144, 113-130. (2020)","DOI":"10.1016\/j.eswa.2019.113100"},{"key":"ref28","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), 28-34. (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","unstructured":"Simonyan, K., Zisserman, A., Zhang, J. S., Hu, J., Li, J.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv preprint arXiv: 1409.1556 (2020)"},{"key":"ref30","unstructured":"Abhronil, S., Ye, Y., Wang, R., Liu, C., Roy, K.: Going Deeper in Spiking Neural Networks: VGG and Residual Architectures. Neuroscience. Vol. 13, 95-95. (2009)"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. arXiv preprint arXiv: 1611.05431 (2016)","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref32","unstructured":"Fei, W., Jiang, M., Qian, C., Yang, S., Li, C.: Residual Attention Network for Image Classification. In IEEE conference on computer vision and pattern recognition (CVPR), 6450-6458. (2017)"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"Yang, K. Y., Qinami, K., Li, F. F., Deng, J., Olga, J.: Towards Fairer Datasets: Filtering and Balancing teh Distribution of the People Subtree in the ImageNet Hierarchy. In: Conference on fairness, accountabiility and transparency (FAT) (2020)","DOI":"10.1145\/3351095.3375709"},{"key":"ref34","unstructured":"Olga, R., Deng, J., Su, H., Krause, J., Ma, J.: ImageNet Large Scale Visual Recognition Challenge. International journal of computer vision (IJCV), 1021-1034. (2015)"},{"key":"ref35","doi-asserted-by":"crossref","unstructured":"Deng, J., Berg, A., Li, K., Hu, J., Li, F. F.: What does classifying more than 10,000 image categories tell us? In: Computer Vision-ECCV (2010)","DOI":"10.1007\/978-3-642-15555-0_6"},{"key":"ref36","unstructured":"Russakovsky, O., Li, F. F.: Attribute Learning in Largescale Datasets. In: Computer Vision-ECCV (2010)"},{"key":"ref37","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, F. F.: ImageNet: A Large-Scale Hierarchical Image Database. In: IEEE international conference on computer vision and pattern recognition (CVPR), 1354-1361. (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref38","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, J.: Squeeze-and-excitation networks. In: IEEE conference on computer vision and pattern recognition (CVPR), 7132-7141. New York, USA. NY: IEEE (2019)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"Zhang, Y. L., Li, K. P., Li, K., Wang, L., Zhong, B.: Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In: Computer Vision ECCV. 294-310. (2010)","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref40","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., Kweon, J.: CBAM: Convolutional Block Attention Module. In: Computer Vision-ECCV. 3-19. (2010)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H. W., Xiao, J., Nie, L. H., Liu, W.: SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning. In: IEEE international conference on computer vision and pattern recognition (CVPR). 6298-6306. (2017)","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"Zhao, H. S., Zhang, Y., Shi, J. S., Lin, J., Jia, J.: PSANet: Point-Wise Spatial Attention Network for Scene Parsing. In: Computer Vision-ECCV. 267-283. (2018)","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref43","unstructured":"Meng, X., Huang, Y., Zhang, J. S., Hu, J., Li, J.: Feature selection and enhanced krill herd algorithm for text document clustering. Computing reviews, Vol. 60, No. 8, 318-328. (2019)"},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"Abualigah, L., Diabat, A., Mirjalili, S.: The Arithmetic Optimization Algorithm. Computer Methods in Applied Mechanics and Engineering, 376-389. (2021)","DOI":"10.1016\/j.cma.2020.113609"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"Laith, A., Dalia, Y., Mohamed, A. E., Amir, H. J., Li, J.: Aquila Optimizer: A novel meta-heuristic optimization algorithm, Computers & Industrial Engineering, Vol. 157, 28-41. (2021)","DOI":"10.1016\/j.cie.2021.107250"},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Li, F. F.: Perceptual Losses for Real-Time Style Transfer and Super-Resolution. Springer, 120-138. (2016)","DOI":"10.1007\/978-3-319-46475-6_43"}],"container-title":["Computer Science and Information Systems"],"original-title":[],"language":"en","deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T10:29:24Z","timestamp":1721903364000},"score":1,"resource":{"primary":{"URL":"https:\/\/doiserbia.nb.rs\/Article.aspx?ID=1820-02142300015W"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023]]}},"URL":"https:\/\/doi.org\/10.2298\/csis220714015w","relation":{},"ISSN":["1820-0214","2406-1018"],"issn-type":[{"value":"1820-0214","type":"print"},{"value":"2406-1018","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}