Abstract
Residual network is a deep learning model widely used in various applications of computer vision, such as image processing, semantic classification and video processing. The traditional residual network is susceptible to the interference induced by the adversarial example attack algorithms, which directly affects the security of practical applications. In this work, we propose a new residual neural network based on a global convolutional denoising model. The global convolution is fused with the denoising technique, and the network structure of the global convolution denoising module is redesigned so that the denoising module can be trained end-to-end with the residual neural network. In addition, the gradient information of the network is concealed to enable the neurons to respond to the pixels that are more meaningful to human vision, thus improving the robustness of the network for adversarial example attack algorithms.
Similar content being viewed by others
REFERENCES
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Yo., Generative adversarial networks, Commun. ACM, 2014, vol. 63, no. 11, pp. 139–144. https://doi.org/10.1145/3422622
Yang, J.W., Target tracking and recognition of a moving video image based on convolution feature selection, Int. J. Biometrics, 2021, vol. 13, nos. 2–3, pp. 180–194. https://doi.org/10.1504/IJBM.2021.114646
Shao, H., Liu, H., Zhang, Z., and Shen, J., Research and analysis of video image target tracking algorithm based on significance, Int. J. High Perform. Syst. Archit., 2018, vol. 8, no. 1/2, pp. 82–93. https://doi.org/10.1504/ijhpsa.2018.10015206
Du, P., Zhang, J., and Long, J., Super-sampling by learning-based super-resolution, Int. J. Comput. Sci. Eng., 2020, vol. 21, no. 2, pp. 249–257. https://doi.org/10.1504/ijcse.2020.105731
Shaker Balure, C. and Kini, R.M., Guidance-based improved depth upsampling with better initial estimate, Int. J. Comput. Vision Rob., 2021, vol. 11, no. 1, pp. 109–125. https://doi.org/10.1504/IJCVR.2021.111878
Ghariba, B., Shehata, M., and Mcguire, P., Salient object detection using semantic segmentation technique, Int. J. Comput. Vision Rob., 2022, vol. 12, no. 1, pp. 17–38. https://doi.org/10.1504/ijcvr.2022.119240
Si, H., Shi, Z., Hu, X., Wang, Yi., and Yang, C., Image semantic segmentation based on improved DeepLab V3 model, Int. J. Modell., Identification Control, 2020, vol. 36, no. 2, pp. 116–125. https://doi.org/10.1504/ijmic.2020.116199
Anami, B.S. and Bhandage, V.A., SME feature-based classification of Adavu and posture images of Bharatanatyam dance, Int. J. Arts Technol., 2021, vol. 12, no. 4, pp. 317–334. https://doi.org/10.1504/IJART.2020.112640
Jiang, Yi., Lu, L., and Xu, J., Enhanced view-independent representation method for skeleton-based human action recognition, Int. J. Inf. Commun. Technol., 2021, vol. 19, no. 2, pp. 201–218. https://doi.org/10.1504/IJICT.2021.117047
Wang, B., Deng, J., and Sun, Ya., Image super-resolution algorithm’s research using convolutional sparse coding model, Int. J. Inf. Commun. Technol., 2019, vol. 15, no. 1, pp. 92–106. https://doi.org/10.1504/ijict.2019.102057
Wang, M. and Deng, W.H., Deep visual domain adaptation: A survey, Neurocomputing, 2018, vol. 312, pp. 135–153. https://doi.org/10.1016/j.neucom.2018.05.083
Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Yo., Zhu, H., Xiong, H., and He, Q., A comprehensive survey on transfer learning, Proc. IEEE, 2020, vol. 109, no. 1, pp. 43–76. https://doi.org/10.1109/jproc.2020.3004555
Li, L., Zhou, Zh., Wang, B., Miao, L., An, Zh., and Xiao, X., Domain adaptive ship detection in optical remote sensing images, Remote Sensing, 2021, vol. 13, no. 16, p. 3168. https://doi.org/10.3390/rs13163168
Na, H. and Park, J.-S., Accented speech recognition based on end-to-end domain adversarial training of neural networks, Appl. Sci., 2021, vol. 11, no. 18, p. 8412. https://doi.org/10.3390/app11188412
Tian, Q., Zhou, J., and Chu, Yi., Joint bi-adversarial learning for unsupervised domain adaptation, Knowl.-Based Syst., 2022, vol. 248, p. 108903. https://doi.org/10.1016/j.knosys.2022.108903
Ganin, Ya., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., and Lempitsky, V., Domain-adversarial training of neural networks, Domain Adaptation in Computer Vision Applications, Springer International Publishing, 2016, vol. 17, pp. 189–209. https://doi.org/10.1007/978-3-319-58347-1_10
Geng, J., Deng, X., Ma, X., and Jiang, W., Transfer learning for SAR image classification via deep joint distribution adaptation networks, IEEE Trans. Geosci. Remote Sensing, 2020, vol. 58, no. 8, pp. 5377–5392. https://doi.org/10.1109/TGRS.2020.2964679
Kishan Babu, K. and Ram Dubey, Sh., CDGAN: Cyclic discriminative generative adversarial networks for image-to-image transformation, J. Visual Commun. Image Representation, 2022, vol. 82, p. 103382. https://doi.org/10.1016/j.jvcir.2021.103382
Saito, K., Watanabe, K., Ushiku, Yo., and Harada, T., Maximum classifier discrepancy for unsupervised domain adaptation, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Sydney, 2017, IEEE, 2017, pp. 2988–2997. https://doi.org/10.1109/cvpr.2018.00392
Pei, Z., Cao, Z., Long, M., and Wang, J., Multi-adversarial domain adaptation, Proc. AAAI Conf. Artif. Intell., 2018, vol. 32, no. 1, pp. 3934–3941. https://doi.org/10.1609/aaai.v32i1.11767
Yu, K., Han, H., Fu, Q., Ma, H., and Zeng, J., Symmetric co-training based unsupervised domain adaptation approach for intelligent fault diagnosis of rolling bearing, Meas. Sci. Technol., 2020, vol. 31, no. 11, p. 115008. https://doi.org/10.1088/1361-6501/ab9841
Long, M.S., Cao, Z.J., and Wang, J.M., Analysis of representations for domain adaptation, Advances in Neural Information Processing Systems 19, Montréal: The MIT Press, 2018, pp. 1640–1650. https://doi.org/10.7551/mitpress/7503.003.0022
Sankaranarayanan, S., Balaji, Yo., Castillo, C., and Chellappa, R., Generate to adapt: Aligning domains using generative adversarial networks, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, 2018, pp. 8503–8512. https://doi.org/10.1109/cvpr.2018.00887
Hu, L., Kan, M., Shan, S., and Chen, X., Duplex generative adversarial network for unsupervised domain adaptation, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, 2018, pp. 1498–1507. https://doi.org/10.1109/cvpr.2018.00162
Zhang, J., Ding, Z., Li, W., and Ogunbona, P., Importance weighted adversarial nets for partial domain adaptation, 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, Salt Lake City, 2018, IEEE, 2018, pp. 8156–8164. https://doi.org/10.1109/cvpr.2018.00851
Cao, Z., Ma, L., Long, M., and Wang, J., Partial adversarial domain adaptation, Computer Vision – ECCV 2018, Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y., Eds., Lecture Notes in Computer Science, vol. 11212, Cham: Springer, 2018, pp. 139–155. https://doi.org/10.1007/978-3-030-01237-3_9
He, K., Zhang, X., Ren, Sh., and Sun, J., Deep residual learning for image recognition, 2016 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, IEEE, 2016, pp. 770–778. https://doi.org/10.1109/cvpr.2016.90
Yan, H., Ding, Yu., Li, P., Wang, Q., Xu, Yo., and Zuo, W., Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation, 2017 IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Honolulu, 2017, IEEE, 2017, pp. 2272–2281. https://doi.org/10.1109/cvpr.2017.107
Kajkamhaeng, S. and Chantrapornchai, C., SE-SqueezeNet: SqueezeNet extension with squeeze-and-excitation block, Int. J. Comput. Sci. Eng., 2021, vol. 24, no. 2, pp. 185–199. https://doi.org/10.1504/ijcse.2021.115105
Al-Barazanchi, H.A., Qassim, H., and Verma, A., Large-scale scene image categorisation with deep learning-based model, Int. J. Comput. Vision Rob., 2020, no. 3, p. 10. https://doi.org/10.1504/IJCVR.2020.107239
Kamada, S. and Ichimura, T., Fine tuning of adaptive learning of deep belief network for misclassification and its knowledge acquisition, Int. J. Comput. Intell. Stud., 2017, vol. 6, no. 4, pp. 333–348. https://doi.org/10.1504/ijcistudies.2017.089511
Tan, Z., Hu, Yu., Luo, D., Hu, M., and Liu, K., The clothing image classification algorithm based on the improved Xception model, Int. J. Comput. Sci. Eng., 2020, vol. 23, no. 3, pp. 214–223. https://doi.org/10.1504/ijcse.2020.111426
Lavinia, Yu., Vo, H., and Verma, A., New colour fusion deep learning model for large-scale action recognition, Int. J. Comput. Vision Rob., 2020, vol. 10, no. 1, pp. 41–60. https://doi.org/10.1504/IJCVR.2020.104356
Muralimohanbabu, Y. and Radhika, K., Multi spectral image classification based on deep feature extraction using deep learning technique, Int. J. Bioinf. Res. Appl., 2021, vol. 17, no. 3, pp. 250–261. https://doi.org/10.1504/IJBRA.2021.117169
Kamada, S. and Ichimura, T., Fast training of adaptive structural learning method of deep learning for multi modal data, Int. J. Comput. Intell. Stud., 2018, vol. 7, no. 3/4, pp. 169–191. https://doi.org/10.1504/ijcistudies.2018.10017446
Too, E.C., Yujian, L., Gadosey, P., Njuki, S., and Essaf, F., Performance analysis of nonlinear activation function in convolution neural network for image classification, Int. J. Comput. Sci. Eng., 2020, vol. 21, no. 4, pp. 522–535. https://doi.org/10.1504/ijcse.2020.106866
Handa, A., Kohli, N., and Agarwal, R., Incremental approach for multi-modal face expression recognition system using deep neural networks, Int. J. Comput. Vision Rob., 2021, vol. 11, no. 1, pp. 1–20. https://doi.org/10.1504/ijcvr.2021.10033651
Pal, N., Rathore, S., and Prasad, L., A comprehensive review of deep learning models for plant disease identification and prediction, Int. J. Eng. Syst. Modell. Simul., 2021, vol. 12, nos. 2–3, pp. 165–179. https://doi.org/10.1504/IJESMS.2021.115530
Wang, J., Wang, R., Dong, L., Yan, D., Zhang, X., and Lin, Yu., Towards breaking DNN-based audio steganalysis with GAN, Int. J. Auton. Adapt., 2021, vol. 14, no. 4, pp. 371–383. https://doi.org/10.1504/IJAACS.2021.119119
Funding
2021 Ministry of Education Industry-University Cooperation Collaborative Education Project, no. 202102348014. 2022 Jiangxi University of Science and Technology Natural Science and Technology Project, no. ZR2101, Project name: Research on blockchain consensus algorithm and its application in IoT data assetization.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The author declares that he has no conflicts of interest.
About this article
Cite this article
Aiping Cai Adversarial Sample Generation Method Based on Global Convolution Noise Reduction Model. Aut. Control Comp. Sci. 57, 389–399 (2023). https://doi.org/10.3103/S0146411623040028
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411623040028