(48-6) 18 * << * >> * Russian * English * Content * All Issues

Attention modules in convolutional neural networks for small object recognition
D.I. Krasnov 1

1 ITMO University,
197101, Saint Petersburg, Russia, Kronverkskiy Prospekt 49, bldg. A

 PDF, 4759 kB

DOI: 10.18287/2412-6179-CO-1468

Pages: 963-968.

Full text of article: Russian language.

Abstract:
A problem of small object recognition is frequently encountered in biomedical and security systems. However, the detection of such objects is often complicated by presence of dense clouds or infrastructure objects. Results of using various attention mechanisms to improve accuracy in small objects segmentation with convolutional neural networks are presented in this paper. Modules of channel attention and spatial attention are considered. This approach allows one to effectively suppress less informative channels and image areas, while enhancing more informative channels and image areas. Meanwhile, weights of the attention modules are automatically adapted to the input data during training. An assessment of influence of the attention mechanisms in convolutional neural network architecture on the ability to suppress complex backgrounds (clouds and infrastructure objects) and segment small objects is performed. The results are presented in the form of tables with test metrics and figures with precision-recall curves, ROC curves and heatmaps showing an effectiveness of background suppression. The results obtained allow one to implement the described attention modules in the convolutional neural networks of any complexity and increase the recognition accuracy of objects of 10-40 pixels in size on a complex background.

Keywords:
semantic segmentation, small object, convolutional neural network, attention modules, computer vision.

Citation:
Krasnov DI. Attention modules in convolutional neural networks for small object recognition. Computer Optics 2024; 48(6): 963-968. DOI: 10.18287/2412-6179-CO-1468.

References:
  1. Chattopadhyay A, Maitra M. MRI-based brain tumour image detection using CNN based deep learning method. Neurosci Inform 2022; 2(4): 100060. DOI: 10.1016/j.neuri.2022.100060.
  2. Hashib H, Leon M, Salaque AM. Object detection based security system using machine learning algorithm and Raspberry Pi. 2019 Int Conf on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2) 2019: 1-4. DOI: 10.1109/IC4ME247184.2019.9036531.
  3. Wang X, Lv G, Xu L. Infrared dim target detection based on visual attention. Infrared Phys Techn 2012; 55(6): 513-521. DOI: 10.1016/j.infrared.2012.08.004.
  4. Chen CLP, Li H, Wei Y, Xia T, Tang YY. A local contrast method for small infrared target detection. IEEE Trans Geosci Remote Sens 2014; 52(1): 574-581. DOI: 10.1109/TGRS.2013.2242477.
  5. Wang H, Xin Y. Wavelet-based contourlet transform and kurtosis map for infrared small target detection in complex background. Sensors 2020; 20(3): 755. DOI: 10.3390/s20030755.
  6. Stojnić V, Risojević V, Muštra M, Jovanović V, Filipi J, Kezić N, Babić Z. A method for detection of small moving objects in UAV videos. Remote Sens 2021; 13(4): 653. DOI: 10.3390/rs13040653.
  7. Liu X, Li X, Li L, Su X, Chen F. Dim and small target detection in multi-frame sequence using Bi-Conv-LSTM and 3D-Conv structure. IEEE Access 2021; 9: 135845-135855. DOI: 10.1109/ACCESS.2021.3110395.
  8. Mazurek P. Convolutional neural network reference for track-before-detect applications. Remote Sens 2023; 15(18): 4629. DOI: 10.3390/rs15184629.
  9. Wang Z, Wang C, Chen Y, Li J. Target detection algorithm based on super- resolution color remote sensing image reconstruction. J Meas Eng 2023; 12(1): 15. DOI: 10.21595/jme.2023.23510.
  10. Liu H, Ding M, Li S, Xu Y, Gong S, Kasule AN. Small-target detection based on an attention mechanism for apron-monitoring systems. Appl Sci 2023; 13(9): 5231. DOI: 10.3390/app13095231.
  11. Fan M, Tian S, Liu K, Zhao J, Li Y. Infrared small target detection based on region proposal and CNN classifier. Signal Image Video P 2021; 15: 1927-1936. DOI: 10.1007/s11760-021-01936-z.
  12. Li B, Xiao C, Wang L, Wang Y, Lin Z, Li M, An W, Guo Y. Dense nested attention network for infrared small target detection. IEEE Trans Image Process 2023; 32: 1745-1758. DOI: 10.1109/TIP.2022.3199107.
  13. Li J, Ye DH, Kolsch M, Wachs JP, Bouman CA. Fast and robust UAV to UAV detection and tracking from video. IEEE Trans Emerg Top Comput 2022; 10(3): 1519-1531. DOI: 10.1109/TETC.2021.3104555.
  14. Svanström F, Englund C, Alonso-Fernandez F. Real-time drone detection and tracking with visible, thermal and acoustic sensors. 25th Int Conf on Pattern Recognition (ICPR) 2020: 7265-7272. DOI: 10.1109/ICPR48806.2021.9413241.
  15. Rozantsev A, Lepetit V, Fua P. Flying objects detection from a single moving camera. 2015 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2015: 4128-4136. DOI: 10.1109/CVPR.2015.7299040.
  16. Wang Y, Zhou Q, Xiong J, Wu X, Jin X. ESNet: An efficient symmetric network for real-time semantic segmentation. In Book: Lin Z, Wang L, Yang J, Shi G, Tan T, Zheng N, Chen X, Zhang Y, eds. Pattern Recognition and Computer Vision. Cham: Springer Nature Switzerland AG; 2019: 41-52. DOI: 10.1007/978-3-030-31723-2_4.
  17. Huang L, Chen C, Yun J, Sun Y, Tian J, Hao Z, Yu H, Ma H. Multi-scale feature fusion convolutional neural network for indoor small target detection. Front Neurorobot 2022; 16: 881021. DOI: 10.3389/fnbot.2022.881021.
  18. Agac S, Durmaz Incel O. On the use of a convolutional block attention module in deep learning-based human activity recognition with motion sensors. Diagnostics 2023; 13(11): 1861. DOI: 10.3390/diagnostics13111861.
  19. Sudre CH, Li W, Vercauteren T, Ourselin S, Jorge Cardoso M. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Book: Cardoso MJ, Arbel T, Carneiro G, et al, eds. Deep learning in medical image analysis and multimodal learning for clinical decision support. Cham: Springer International Publishing AG; 2017: 240-248. DOI: 10.1007/978-3-319-67558-9_28.
  20. Rezatofighi H, Tsoi N, Gwak JY, Sadeghian A, Reid I, Savarese S. Generalized intersection over union: A metric and a loss for bounding box regression. 2019 IEEE/CVF Conf on Computer Vision and Pattern Recognition (CVPR) 2019: 658-666. DOI: 10.1109/CVPR.2019.00075.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20