基于BGNet边缘与上下文融合的改进
Improvement of Edge and Context Fusion Based on BGNet
摘要: 伪装目标的检测是一项极具价值和挑战性的任务，针对现有深度学习网络对于伪装目标识别率不高、边缘识别不精准等问题，本文提出一种基于BGNet改进的边缘双注意力自适应融合与上下文融合的伪装目标识别模型(TGDNet)，具有更优的分割识别性能。本文使用CAMO、CHAMELEON、COD10K、NC4K数据集进行训练，与SINET、UGTR、LSR等神经网络模型对比测试，测试结果表明我们提出的TGDNet模型收敛速度快且稳定，在关键指标S-measure、E-measure、F-measure、MAE上均优于对比模型。
Abstract: The detection of disguised targets is a highly valuable and challenging task. In response to the low recognition rate and inaccurate edge recognition of existing deep learning networks for disguised targets, a disguised target recognition model (TGDNet) based on improved edge dual-attention adaptive fusion and context fusion of BGNet is proposed in this paper to improve its segmentation and recognition performance. This article uses the CAMO, CHAMELEON, COD10K, and NC4K datasets for training, and compares them with neural network models such as SINET, UGTR, LSR, etc. The test results show that our proposed TGDNet model has fast and stable convergence speed, and outperforms the comparison model in key indicators, including S-measure, E-measure, F-measure, and MAE.
文章引用：武新浩. 基于BGNet边缘与上下文融合的改进[J]. 计算机科学与应用, 2025, 15(10): 24-33. https://doi.org/10.12677/csa.2025.1510247

参考文献

[1] Fan, D., Ji, G., Sun, G., Cheng, M., Shen, J. and Shao, L. (2020) Camouflaged Object Detection. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 2774-2784. [Google Scholar] [CrossRef] 
[2] Sun, Y., Chen, G., Zhou, T., Zhang, Y. and Liu, N. (2021) Context-Aware Cross-Level Fusion Network for Camouflaged Object Detection. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Montreal, 19-27 August 2021, 1025-1031. [Google Scholar] [CrossRef] 
[3] Wang, K., Bi, H., Zhang, Y., Zhang, C., Liu, Z. and Zheng, S. (2022) D2C-Net: A Dual-Branch, Dual-Guidance and Cross-Refine Network for Camouflaged Object Detection. IEEE Transactions on Industrial Electronics, 69, 5364-5374. [Google Scholar] [CrossRef] 
[4] Ren, J.J., Hu, X.W., Zhu, L., et al. (2021) Deep Texture-Aware Features for Camouflaged Object Detection. IEEE Transactions on Circuits and Systems for Video Technology, 33, 1157-1167.
[5] Mei, H., Ji, G., Wei, Z., Yang, X., Wei, X. and Fan, D. (2021) Camouflaged Object Segmentation with Distraction Mining. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 8768-8777. [Google Scholar] [CrossRef] 
[6] Fan, D., Ji, G., Cheng, M. and Shao, L. (2022) Concealed Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 6024-6042. [Google Scholar] [CrossRef] [PubMed]
[7] Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M. and Jagersand, M. (2019) BASNet: Boundary-Aware Salient Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 7471-7481. [Google Scholar] [CrossRef] 
[8] Fan, D., Ji, G., Zhou, T., Chen, G., Fu, H., Shen, J., et al. (2020) PraNet: Parallel Reverse Attention Network for Polyp Segmentation. In: Martel, A.L., et al., Eds., Medical Image Computing and Computer Assisted Intervention—MICCAI 2020, Springer, 263-273. [Google Scholar] [CrossRef] 
[9] Fan, D., Gong, C., Cao, Y., Ren, B., Cheng, M. and Borji, A. (2018) Enhanced-Alignment Measure for Binary Foreground Map Evaluation. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, 13-19 July 2018, 698-704. [Google Scholar] [CrossRef] 
[10] Fan, D., Cheng, M., Liu, Y., Li, T. and Borji, A. (2017) Structure-Measure: A New Way to Evaluate Foreground Maps. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 4558-4567. [Google Scholar] [CrossRef] 
[11] Margolin, R., Zelnik-Manor, L. and Tal, A. (2014) How to Evaluate Foreground Maps. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 248-255. [Google Scholar] [CrossRef]