{"id":3693,"date":"2026-04-12T22:42:09","date_gmt":"2026-04-12T14:42:09","guid":{"rendered":"https:\/\/iweb20wp-b205b.url.tku.edu.tw\/jase\/?post_type=tkuisotope&p=3693"},"modified":"2026-04-26T20:08:42","modified_gmt":"2026-04-26T12:08:42","slug":"jase-202609-32-002","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202609-32-002","title":{"rendered":"Efficient Feature Extraction with Multi-Scale Attention Mechanism: A Lightweight Deep Learning Framework for Image Classification"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 32<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Xinwei Liu<\/i><\/a><\/p>\n\n\n\n

College of Economic and Management, Shenyang Institute of Technology, Shenyang 113122 China<\/p>\n<\/div>\n\n\n\n

\n

Received: January 28, 2026
Accepted: March 9, 2026
Publication Date: April 12, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Architecture of the Efficient Multi-Scale Attention (EMA) module<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:  BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202609_32.002<\/a>  <\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Deep learning-based image classification has achieved remarkable progress in recent years, but the contradiction between model performance and computational efficiency remains a critical challenge for edge-device deployment. To address this issue, this paper proposes a lightweight deep learning framework integrated with an efficient multi-scale attention (EMA) module for high-performance feature extraction. The EMA module adopts a channel-grouping strategy and parallel multi-branch architecture to capture multi-scale contextual information without dimensionality reduction, which effectively avoids the loss of feature details caused by traditional attention mechanisms. Specifically, it divides input features into multiple subgroups and employs 1 \u00d71 and 3\u00d73 convolutional branches to model local and global dependencies respectively, followed by cross-spatial learning to fuse complementary features across branches. The proposed framework is evaluated on three benchmark datasets (CIFAR-100, ImageNet-1k, and Tiny-ImageNet) against state-of-the-art lightweight models and attention mechanisms. Experimental results demonstrate that the proposed framework achieves a better trade-off between classification accuracy and computational cost. The proposed framework provides a promising solution for efficient image classification in resource-constrained scenarios.<\/p>\n\n\n\n

Keywords: Image Classification; Lightweight Deep Learning; Multi-Scale Attention; Feature<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
    \n
  1. [1] X. Meng, X. Wang, S. Yin, and H. Li,(2023)\u201cFew-shot image classification algorithm based on attention mechanism and weight fusion “Journal of Engineering and AppliedScience70(1):14.DOI:10.1186\/s44147-023-00186-9.<\/li>\n
  2. [2] L. Wang, H. Wang, S. Yin, and L. Wang, (2025) \u201cMasked vision transformer for fast hyperspectral image classification\u201d IEEE Transactions on Geoscience and Remote Sensing 63: DOI: 10.1109 \/ TGRS . 2025 . 3572242.<\/li>\n
  3. [3] Y. Wang, Y. Deng, Y. Zheng, P. Chattopadhyay, and L. Wang, (2025) \u201cVision transformers for image classification: A comparative survey\u201d Technologies 13(1): 32. DOI: 10.3390\/technologies13010032.<\/li>\n
  4. [4] H. Song, H. Xie, Y. Duan, X. Xie, F. Gan, W. Wang, and J. Liu, (2025) \u201cPure data correction enhancing remote sensing image classification with a lightweight ensemble model\u201d Scientific Reports 15(1): 5507. DOI: 10.1038\/s41598-025-89735-1.<\/li>\n
  5. [5] Y. Shao, J. Yang, W. Zhou, H. Sun, and Q. Gao, (2025) \u201cFractal-Inspired Region-Weighted Optimization and Enhanced MobileNet for Medical Image Classification\u201d Fractal and Fractional 9(8): 511. DOI: 10.3390\/fractalfract9080511.<\/li>\n
  6. [6] Q. Du, Z. Liu, Y. Song, N. Wang, Z. Ju, and S. Gao, (2025) \u201cA lightweight dendritic shufflenet for medical image classification\u201d IEICE Transactions on Information and Systems: 2024EDP7059. DOI: 10.1587\/transinf.2024EDP7059.<\/li>\n
  7. [7] G. Sangar and V. Rajasekar, (2025) \u201cOptimized classification of potato leaf disease using EfficientNet-LITE and KE-SVM in diverse environments\u201d Frontiers in plant science 16: 1499909. DOI: 10.3389\/fpls.2025.1499909.<\/li>\n
  8. [8] S. Zheng and Y. Wang, (2025) \u201cSF Net: A Pyramid-Based Feature Fusion Convolutional Neural Network With Embedded Squeeze-and-Excitation Mechanism for Retinal OCT Image Classification\u201d International Journal of Imaging Systems and Technology 35(5): e70197. DOI: 10.1002\/ima.70197.<\/li>\n
  9. [9] C. Zhuang, X. Yuan, L. Gu, Z. Wei, Y. Fan, and X. Guo, (2025) \u201cFrequency Regulated Channel-Spatial Attention module for improved image classification\u201d Expert Systems with Applications 260: 125463. DOI: 10.1016\/j.eswa.2024.125463.<\/li>\n
  10. [10] R. Shang, M. Hu, J. Feng, W. Zhang, and S. Xu, (2025) \u201cA lightweight PolSAR image classification algorithm based on multi-scale feature extraction and local spatial information perception\u201d Applied Soft Computing 170: 112676. DOI: 10.1016\/j.asoc.2024.112676.<\/li>\n
  11. [11] T. Jinaga, B. Banothu, S. Nickolas, and G. R. Patil, (2025) \u201cAn Adaptive Lightweight Sequence Space Model for Medical Image Classification\u201d SN Computer Science 6(7): 892. DOI: 10.1007\/s42979-025-04387-2.<\/li>\n
  12. [12] D. Ouyang, S. He, G. Zhang, M. Luo, H. Guo, J. Zhan, and Z. Huang. \u201cEfficient multi-scale attention module with cross-spatial learning\u201d. In: ICASSP 2023-2023 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE. 2023, 1\u20135. DOI: 10.1109\/ICASSP49357.2023.10096516.<\/li>\n
  13. [13] L. Liu, B. Zhou, Q. Li, G. Fu, Y. Wang, and H. Chu, (2025) \u201cParallel joint encoding for drone-view object detection under low-light conditions\u201d Frontiers in Artificial Intelligence 8: 1622100. DOI: 10.3389\/frai.2025.1622100.<\/li>\n
  14. [14] B. Guan, G. Chu, Z. Wang, J. Li, and B. Yi, (2025) \u201cInstance-level semantic segmentation of nuclei based on multimodal structure encoding\u201d BMC bioinformatics 26(1): 42. DOI: 10.1186\/s12859-025-06066-8.<\/li>\n
  15. [15] R. Boukhenoun, H. Doghmane, K. Messaoudi, and E.-B. Bourennane, (2025) \u201cComparative Analysis of CNN Performances Using CIFAR-100 and MNIST Databases: GPU vs. CPU Efficiency\u201d Recent Advances in Electrical & Electronic Engineering 18(10): 2025\u20132037. DOI: 10.2174\/0123520965348453250226080233.<\/li>\n
  16. [16] L. Teng, H. Li, and Y. Si, \u201cNeural Tensor Network And Adaptive Graph Convolution For Sports\u201d Journal of Applied Science and Engineering 29(6): 1483\u20131491. DOI: 10.6180\/jase.202606_29(6).0015.<\/li>\n
  17. [17] V. Pentsos, S. Tragoudas, K. Nagesh Gowda, and M. Schmit, (2026) \u201cImproved Image Classification using Lightweight Deep Neural Network Enhancements\u201d ACM Transactions on Intelligent Systems and Technology 17(1): 1\u201326. DOI: 10.1145\/3779421.<\/li>\n
  18. [18] S. Yin, L. Wang, T. Chen, H. Huang, J. Gao, J. Zhang, M. Liu, P. Li, and C. Xu, (2025) \u201cLKAFormer: A lightweight kolmogorov-arnold transformer model for image semantic segmentation\u201d ACM Transactions on Intelligent Systems and Technology: DOI: 10.1145\/3759254.<\/li>\n
  19. [19] Z. Liu, Z. Sun, Y. Zang, W. Li, P. Zhang, X. Dong, Y. Xiong, D. Lin, and J. Wang, (2026) \u201cRar: Retrieving and ranking augmented mllms for visual recognition\u201d IEEE Transactions on Image Processing 35: 388\u2013401. DOI: 10.1109\/TIP.2025.3644175.<\/li>\n
  20. [20] A. Umamageswari, S. Deepa, and K. Raja. \u201cDeep Learning and Image Processing for Cancer Cell Identification\u201d. In: AI in Diagnostic Radiology: Clinical Applications and Case-Based Insights. IGI Global Scientific Publishing, 2026, 1\u201340. DOI: 10.4018\/979-8-3373-5801-7.ch001.<\/li>\n<\/ol>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,720,6],"tags":[722],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:  BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202609_32.002   Download PDF Deep learning-based image classification has achieved remarkable progress in recent years,…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/3693"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3693"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3693"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3693"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}