• Optics and Precision Engineering
  • Vol. 33, Issue 1, 123 (2025)
He YAN*, Qiuxia LEI, and Xu WANG
Author Affiliations
  • Liangjiang College of Artificial Intelligence, Chongqing University of Technology, Chongqing401135, China
  • show less
    DOI: 10.37188/OPE.20253301.0123 Cite this Article
    He YAN, Qiuxia LEI, Xu WANG. Improved DeepLabv3+ semantic segmentation incorporating attention mechanisms[J]. Optics and Precision Engineering, 2025, 33(1): 123 Copy Citation Text show less
    References

    [1] F L REN, L YANG, H B ZHOU et al. Real-time semantic segmentation based on improved BiSeNet. Opt. Precision Eng., 31, 1217-1227(2023).

         任凤雷, 杨璐, 周海波. 基于改进BiSeNet的实时图像语义分割. 光学 精密工程, 31, 1217-1227(2023).

    [2] B K CHEN, C GONG, J YANG. Importance-aware semantic segmentation for autonomous vehicles. IEEE Transactions on Intelligent Transportation Systems, 20, 137-148.

    [3] L C CHEN, G PAPANDREOU, F SCHROFF et al. Rethinking atrous convolution for semantic image segmentation, 1706-05587. https://arxiv.org/abs/1706.05587v3

    [4] J LONG, E SHELHAMER, T DARRELL. Fully convolutional networks for semantic segmentation, 7, 3431-3440(2015).

    [5] O RONNEBERGER, P FISCHER, T BROX. U-Net: Convolutional Networks for Biomedical Image Segmentation, 234-241(2015).

    [6] R STRUDEL, R GARCIA, I LAPTEV et al. Segmenter: transformer for semantic segmentation, 10, 7262-7272(2021).

    [7] A KIRILLOV, E MINTUN, N RAVI et al. Segment anything, 1, 4015-4026(2023).

    [8] 赵为平, 陈雨, 项松. 基于改进的DeepLabv3+图像语义分割算法研究. 系统仿真学报, 35, 2333-2344(2023).

         W P ZHAO, Y CHEN, S XIANG et al. Image semantic segmentation algorithm based on improved DeepLabv3+. Journal of System Simulation, 35, 2333-2344(2023).

    [9] L C CHEN, Y K ZHU, G PAPANDREOU et al. Encoder-decoder with atrous separable convolution for semantic image segmentation, 833-851(2018).

    [10] X T WANG, H YAN, J Q LIU et al. A new deeplabv3+ semantic segmentation model of edge gradient interpolation with double branch structure. CAAI Transactions on Intelligent Systems, 18, 604-612(2023).

         王潇棠, 闫河, 刘建骐. 一种边缘梯度插值的双分支deeplabv3+语义分割模型. 智能系统学报, 18, 604-612(2023).

    [11] 周羿, 刘德儿. 融合注意力机制及DenseASPP改进的DeeplabV3+遥感图像分割方法. 遥感信息, 38, 85-92(2023).

         Y ZHOU, D E LIU. A semantic segmentation method for remote sensing image based on fusion attention mechanism and DenseASPP improved DeeplabV3+. Remote Sensing Information, 38, 85-92(2023).

    [12] M SANDLER, A HOWARD, M L ZHU et al. MobileNetV2: inverted residuals and linear bottlenecks, 18, 4510-4520(2018).

    [13] D C HAN, T Z YE, Y Z HAN et al. Agent attention: on the integration of softmax and linear attention, 2312-08874. https://arxiv.org/abs/2312.08874v3

    [14] L Yang, R Y Zhang, L Li et al. Simam: A simple, parameter-free attention module for convolutional neural networks, 11863-11874(2021).

    [15] X Z ZHU, D Z CHENG, Z ZHANG et al. An empirical study of spatial attention mechanisms in deep networks, 6688-6697(2019).

    [16] Z L HUANG, X G WANG, L C HUANG et al. CCNet: criss-cross attention for semantic segmentation, 603-612(2019).

    [17] Y H YUAN, X L CHEN, J D WANG. Object-contextual Representations for Semantic Segmentation, 173-190(2020).

    [18] M H GUO, Z N LIU, T J MU et al. Beyond self-attention: external attention using two linear layers for visual tasks. IEEE Trans Pattern Anal Mach Intell, 45, 5436-5447(2023).

    [19] X R PAN, C J GE, R LU et al. On the integration of self-attention and convolution, 18, 815-825(2022).

    [20] Z H LIN, M W FENG, C N DOS SANTOS et al. A structured self-attentive sentence embedding, 1703-03130. https://arxiv.org/abs/1703.03130v1

    [21] D J YU, H L WANG, P Q CHEN et al. Mixed Pooling for Convolutional Neural Networks. Rough Sets and Knowledge Technology, 364-375(2014).

    [22] T Y HSIAO, Y C CHANG, H H CHOU et al. Filter-based deep-compression with global average pooling for convolutional networks. Journal of Systems Architecture, 95, 9-18(2019).

    [23] T H CHENG, X G WANG, L C HUANG et al. Boundary-preserving Mask R-CNN, 660-676(2020).

    [24] Y H YUAN, J Y XIE, X L CHEN et al. SegFix: Model-agnostic Boundary Refinement for Segmentation, 489-506(2020).

    [25] X G ZHANG, L Z DING, Y F LIU et al. FDA-DeepLab semantic segmentation network based on dual attention module. Journal of Southeast University (Natural Science Edition), 52, 1145-1151(2022).

         张小国, 丁立早, 刘亚飞. 基于双注意力模块的FDA-DeepLab语义分割网络. 东南大学学报(自然科学版), 52, 1145-1151(2022).

    [26] G P XU, W T LIAO, X ZHANG et al. Haar wavelet downsampling: a simple but effective downsampling module for semantic segmentation. Pattern Recognition, 143, 109819(2023).

    [27] M EVERINGHAM, ESLAMI S MALI, L VAN GOOL et al. The pascal visual object classes challenge: a retrospective. International Journal of Computer Vision, 111, 98-136(2015).

    [28] Q L WANG, B G WU, P F ZHU et al. ECA-net: efficient channel attention for deep convolutional neural networks, 13, 11534-11542(2020).

    CLP Journals

    [1] Hui LIU, Jin LIANG, Meitu YE, Jianying GUO, Leigang LI. Comparison of deviation in aircraft casing deformation measurement based on data mapping optimization[J]. Optics and Precision Engineering, 2023, 31(20): 2930

    [2] Jianying GUO, Jin LIANG, Meitu YE, Mingming WANG, Wei SHI. Mirror-assisted multi-view measurement of 3D deformation for aero-engine casing[J]. Optics and Precision Engineering, 2022, 30(24): 3105

    He YAN, Qiuxia LEI, Xu WANG. Improved DeepLabv3+ semantic segmentation incorporating attention mechanisms[J]. Optics and Precision Engineering, 2025, 33(1): 123
    Download Citation