https://doi.org/10.4081/jae.2024.1606

Fine-grained recognition algorithm of crop pests based on cross-layer bilinear aggregation and multi-task learning

Vol. 55 No. 3 (2024)
Published: 30 October 2024
Agricultural engineering, lightweight network, cross-layer bilinear aggregation, multi-task learning, fine-grained recognition
Abstract Views: 195
PDF: 128
HTML: 1
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Authors

Juquan Ruan
https://orcid.org/0009-0004-3758-7623
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
Shuo Liu
874477154@qq.com
https://orcid.org/0000-0002-3724-0353
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
Wanjing Mao
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
Shan Zeng
https://orcid.org/0000-0002-1759-9385
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
Zhuoyi Zhang
https://orcid.org/0009-0005-7660-5676
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
Guangsun Yin
https://orcid.org/0009-0009-8449-6245
School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.

Fine-grained recognition of crop pests is a crucial concern in the field of agriculture, as the accuracy of recognition and generalization ability directly affect the yield and quality of crops. Aiming at the characteristics of crop pests with a wide variety of species, small inter-class and large intra-class differences in external morphology, as well as the problems of uneven sample distribution and noisy labels in fine-grained image datasets under complex environments, we propose a fine-grained recognition model of crop pests (MT-MACLBPHSNet) based on cross-layer bilinear aggregation and multi-task learning, which consists of three key modules: the backbone network module, the cross-layer bilinear aggregation module, and the multi-task learning module. A new union loss function is designed in the primary task of the multi-task learning module, which is used to alleviate the two problems existing in the model training fine-grained image datasets. The experimental results show that the model effectively balances the model complexity and recognition accuracy in a comparative analysis with several existing excellent network models on the IP102-CP13 dataset, with the recognition accuracy reaching 75.37%, which is 7.06% higher than the Baseline model, and the F1-score reaching 67.06%. Additionally, the generalization of the model is also verified on the IP102-VP16 dataset, and the model outperforms most of the models in terms of recognition accuracy and generalization ability, which can provide an effective reference for fine-grained recognition of crop pests.

Dimensions

Altmetric

PlumX Metrics

Downloads

Download data is not yet available.

Citations

Crossref
Scopus
Google Scholar
Europe PMC
Amid, E., Warmuth, M.K.K., Anil, R., Koren, T. 2019. Robust bi-tempered logistic loss based on bregman divergences. Proc. 32nd Adv. Neural Inf. Process. Syst., Vancouver. p. 14987-96.
Chang, D., Ding, Y., Xie, J., Bhunia, A.K., Li, X., Ma, Z., Xu, M., Guo, J., Song, Y.Z. 2020. The devil is in the channels: mutual-channel loss for fine-grained image classification. IEEE Trans. Image Process 29:4683-4695. DOI: https://doi.org/10.1109/TIP.2020.2973812
Chen, J., Kao, S., He, H., Zhuo, W., Wen, S., Lee, C., Chan, S. G. 2023. Run, don’t walk: chasing higher FLOPS for faster neural networks. Proc. 36th IEEE Conf. Comput. Vis. Pattern Recog., Vancouver. pp. 12021-31. DOI: https://doi.org/10.1109/CVPR52729.2023.01157
Cipolla, R., Gal, Y., Kendall, A. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. Proc. 31st IEEE Conf. Comput. Vis. Pattern Recog., Salt Lake City. pp. 7482-91. DOI: https://doi.org/10.1109/CVPR.2018.00781
Gao, Y., Beijbom, O., Zhang, N., Darrell, T. 2016. Compact bilinear pooling. Proc. 29th IEEE Conf. Comput. Vis. Pattern Recog., Las Vegas. pp. 317-26. DOI: https://doi.org/10.1109/CVPR.2016.41
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C. 2020. GhostNet: More features from cheap operations. Proc. 33rd IEEE Conf. Comput. Vis. Pattern Recog. Seattle. pp. 1577-1586 DOI: https://doi.org/10.1109/CVPR42600.2020.00165
He, K., Zhang, X., Ren, S., Sun, J. 2016. Deep residual learning for image recognition. Proc. 29th IEEE Conf. Comput. Vis. Pattern Recog, Las Vegas. pp. 770-8. DOI: https://doi.org/10.1109/CVPR.2016.90
Howard, A., Sandler, M., Chu, G., Chen, L.C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., Le, Q.V., Adam, H. 2019. Searching for MobileNetV3. Proc. 17th IEEE Int. Conf. Comput. Vis., Seoul. pp. 1314-24. DOI: https://doi.org/10.1109/ICCV.2019.00140
Kim, J.H., On, K.W., Lim, W., Kim, J., Ha, J.W., Zhang, B.T. 2016. Hadamard product for low-rank bilinear pooling. arXiv:1610.04325.
Li, C., Zhen, T., Li, Z. 2022. Image classification of pests with residual neural network based on transfer learning. Appl. Sci. 12:4356. DOI: https://doi.org/10.3390/app12094356
Li, J., Che, G., An, Y. 2020. Image recognition of Pyrausta nubilalis based on optimized convolutional neural network. J. South China Agric. Univ. 41:110-116.
Li, Y., Wang, H., Dang, L. M., Sdeghi-Niaraki, A., Moon, H. 2020. Crop pest recognition in natural scenes using convolutional neural networks. Comput. Electron. Agric. 169:105174. DOI: https://doi.org/10.1016/j.compag.2019.105174
Li, Y., Yuan, Y. 2017. Convergence analysis of two-layer neural networks with relu activation. Proc. 30th Adv. Neural Inf. Process. Syst., Long Beach. pp. 597-607.
Lin, T.Y., RoyChowdhury, A., Maji, S. 2015. Bilinear CNN models for fine-grained visual recognition. Proc. 15th IEEE Int. Conf. Comput. Vis., Santiago. pp. 1449-57. DOI: https://doi.org/10.1109/ICCV.2015.170
Luo, W., Li, Y., Urtasun, R., Zemel, R. 2016. Understanding the effective receptive field in deep convolutional neural networks. Proc. 29th Adv. Neural Inf. Process. Syst., Barcelona. pp. 4898-906.
Ma, N., Zhang, X., Zheng, H.T., Sun, J. 2018. ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design. Proc. 15th Eur. Conf. Comput. Vis., Munich. pp. 122-38. DOI: https://doi.org/10.1007/978-3-030-01264-9_8
Misra, D. 2019. Mish: A self regularized non-monotonic activation function. arXiv:1908.08681.
Nanni, L., Maguolo, G., Pancino, F. 2020. Insect pest image detection and recognition based on bio-inspired methods. Ecol. Inform. 57:4356. DOI: https://doi.org/10.1016/j.ecoinf.2020.101089
Ruan, J., Liu, S. 2023. Lightweight recognition of crop pests based on high-order residual and attention mechanism. Comp. Syst. Appl. 32:104-115.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C. 2018. MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proc. 31st IEEE Conf. Comput. Vis. Pattern Recog., Salt Lake City. pp. 4510-20. DOI: https://doi.org/10.1109/CVPR.2018.00474
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A. 2015. Going deeper with convolutions. Proc. 28th IEEE Conf. Comput. Vis. Pattern Recog., Boston. pp. 1-9. DOI: https://doi.org/10.1109/CVPR.2015.7298594
Tan, J., Wang, C., Li, B., Li, Q., Quyang, W., Yin, C., Yan J. 2020. Equalization loss for long-tailed object recognition. Proc. 33rd IEEE Conf. Comput. Vis. Pattern Recog., Seattle. pp. 11659-68. DOI: https://doi.org/10.1109/CVPR42600.2020.01168
Tan, M., Le, Q. 2019. EfficientNet: rethinking model scaling for convolutional neural networks. arXiv 1905.11946v5.
Thenmozhi, K., Reddy, U.S. 2019. Crop pest classification based on deep convolutional neural network and transfer learning. Comput. Electron. Agric. 164:104906. DOI: https://doi.org/10.1016/j.compag.2019.104906
Vujović, Ž. 2021. Classification model evaluation metrics. Int. J. Adv. Comput. Sci. Appl. 12:599-606. DOI: https://doi.org/10.14569/IJACSA.2021.0120670
Wang, D., Wang, J., Ren, Z., Li, W. 2022. DHBP: A dual-stream hierarchical bilinear pooling model for plant disease multi-task classification. Comput. Electron. Agric. 195:106788. DOI: https://doi.org/10.1016/j.compag.2022.106788
Wang, J., Li, W., Wang, Y., Tao, R., Du, Q. 2023. Representation-enhanced status replay network for multisource remote-sensing image classification. IEEE Trans. Neural Netw. Learn. Syst. 2023. Online Ahed of Print.
Wang, J., Li, W., Zhang, M., Tao, R., Chanussot, J. 2023. Remote-sensing scene classification via multistage self-guided separation network. IEEE Trans. Geosci. Remote. Sens. 61:1-12. DOI: https://doi.org/10.1109/TGRS.2023.3295797
Wang, M., Wu, Z., Zhou, Z. 2021. [Fine-grained identification research of crop pests and diseases based on improved CBAM via attention].[Article in Chinese]. Trans. Chin. Soc. Agric. Mach. 52:239-247.
Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q. 2020. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proc. 33rd IEEE Conf. Comput. Vis. Pattern Recog., Seattle. pp. 11531-9. DOI: https://doi.org/10.1109/CVPR42600.2020.01155
Wei, D., Chen, J., Luo, T., Long, T., Wang, H. 2022. Classification of crop pests based on multi-scale feature fusion. Comput. Electron. Agric. 194:106736. DOI: https://doi.org/10.1016/j.compag.2022.106736
Wu, X., Zhan, C., Lai, Y.K., Cheng, M.M., Yang, J. 2019. IP102: a large-scale benchmark dataset for insect pest recognition. Proc. 32nd IEEE Conf. Comput. Vis. Pattern Recog., Long Beach. pp. 8779-88. DOI: https://doi.org/10.1109/CVPR.2019.00899
Yu, C., Zhao, X., Zheng, Q., Zhang, P., You, X. 2018. Hierarchical bilinear pooling for fine-grained visual recognition. Proc. 15th Eur. Conf. Comput. Vis., Munich. pp. 595-610. DOI: https://doi.org/10.1007/978-3-030-01270-0_35
Yuan, P., Qian, S., Zhai, Z., Fernán Martínez, J., Xu, H. 2022. Study of chrysanthemum image phenotype on-line classification based on transfer learning and bilinear convolutional neural network. Comput. Electron. Agric. 194:106679. DOI: https://doi.org/10.1016/j.compag.2021.106679
Zhang, M., Li, W., Zhang, Y., Tao, R., Du, Q. 2023. Hyperspectral and LiDAR Data Classification Based on Structural Optimization Transmission. IEEE Trans. Cybern. 53:3153-3164. DOI: https://doi.org/10.1109/TCYB.2022.3169773
Zheng, X., Zheng P., Wang, W., Cheng, Y., Su, Y. 2023. Rice pest recognition based on multi-scale feature extraction depth residual network. J. South China Agric. Univ. 44:438-446.
Zhang, H., Zu, K., Lu, J., Zou, Y., Meng, D. 2022. EPSANet: An efficient pyramid squeeze attention block on convolutional neural network. Proc. 16th Asian Conf. Comput. Vis., Macau. pp. 541-57. DOI: https://doi.org/10.1007/978-3-031-26313-2_33
Zhang, Y., Liu, J., Zuo, X. 2020. Survey of multi-task learning. Chin. J. Comput. 43:1340-1378.
Zhang, Y., Yang, Q. 2021. A survey on multi-task learning. IEEE Trans. Knowl. Data Eng. 34:5586-5609. DOI: https://doi.org/10.1109/TKDE.2021.3070203

Supporting Agencies

Wuhan Polytechnic University

How to Cite

Ruan, J. (2024) “Fine-grained recognition algorithm of crop pests based on cross-layer bilinear aggregation and multi-task learning”, Journal of Agricultural Engineering, 55(3). doi: 10.4081/jae.2024.1606.
Copyright (c) 2024 the Author(s) Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

PAGEPress has chosen to apply the Creative Commons Attribution NonCommercial 4.0 International License (CC BY-NC 4.0) to all manuscripts to be published.