基于稠密扩张卷积的图像语义分割模型
作者:
基金项目:

浙江省重点研发计划(2020C03094)


Image Semantic Segmentation Model Based on Dense Dilation Convolution
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [29]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为解决图像语义分割任务中面对的分割场景的复杂性、分割对象的多样性及分割对象空间位置的差异性问题, 提高语义分割模型的精度, 提出基于稠密扩张卷积的双分支多层级语义分割网络(double branch and multi-stages network, DBMSNet). 首先采用主干网络提取输入图像的4个不同分辨率的特征图(De1、De2、De3、De4), 其次采用特征精炼(feature refine, FR)模块对De1和De3这两个特征图进行特征精炼处理, 特征精炼处理之后的输出分支经过混合扩张卷积模块(mixed dilation module, MDM)编码空间位置特征, De4分支采用金字塔池化模块(pyramid pooling module, PPM)编码高级语义特征, 最后将两个分支进行融合, 输出分割结果. 在数据集CelebAMask-HQ和Cityscapes中进行实验, 分别得到mIoU精度为74.64%、78.29%. 结果表明, 本文方法的分割精度高于对比方法, 且具有更少的参数量.

    Abstract:

    Semantic segmentation is a very challenging task because of the complexity of parsing the scene, the diversity of segmented objects, and the differences in spatial positions of objects. To tackle this dilemma, this paper proposes a novel architecture named double branch and multi-stage network (DBMSNet) based on dense dilated convolution. Firstly, four feature maps (De1, De2, De3, and De4) with different resolutions are extracted by the backbone network, and then the feature refinement maps of De1 and De3 are output through the feature refinement (FR) module. Secondly, the output branch is processed by the mixed dilation module (MDM) to extract rich spatial location features, while the De4 branch is processed by the pyramid pooling module (PPM) to extract multi-scale semantic information. Finally, the two branches are merged and the segmentation result is output. Comprehensive experiments are conducted on two public datasets of CelebAMask-HQ and Cityscapes, on which our model achieves mean intersection-over-union (mIoU) scores of 74.64% and 78.29%, respectively. The results show that the segmentation accuracy of this study is higher than that of the counterpart method, and this method has fewer parameters.

    参考文献
    [1] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4): 640–651. [doi: 10.1109/TPAMI.2016.2572683
    [2] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations. San Diego, 2015. 1–14.
    [3] Szegedy C, Liu W, Jia YQ, et al. Going deeper with convolutions. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 1–9.
    [4] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 770–778.
    [5] Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 2261–2269.
    [6] Wang RJ, Li X, Ling CX. Pelee: A real-time object detection system on mobile devices. Proceedings of the 32nd Conference on Neural Information Processing Systems. Montreal: Curran Associates Inc., 2018. 1967–1976.
    [7] Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions. Proceedings of the 4th International Conference on Learning Representations. San Juan, 2016. 1–13.
    [8] Chen LC, Papandreou G, Kokkinos I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834–848. [doi: 10.1109/TPAMI.2017.2699184
    [9] Zhao HS, Shi JP, Qi XJ, et al. Pyramid scene parsing network. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 6230–6239.
    [10] Fu J, Liu J, Tian HJ, et al. Dual attention network for scene segmentation. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 3141–3149.
    [11] Paszke A, Chaurasia A, Kim S, et al. ENet: A deep neural network architecture for real-time semantic segmentation.arXiv: 1606.02147, 2016.
    [12] Zhao HS, Qi XJ, Shen XY, et al. ICNet for real-time semantic segmentation on high-resolution images. Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018. 418–434.
    [13] Xiong ZQ, Wang ZC, Li J, et al. Using features specifically: An efficient network for scene segmentation based on dedicated attention mechanisms. IEEE Access, 2020, 8: 217947–217956. [doi: 10.1109/ACCESS.2020.3041748
    [14] Chollet F. Xception: Deep learning with depthwise separable convolutions. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 1800–1807.
    [15] Zhang XY, Zhou XY, Lin MX, et al. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 6848–6856.
    [16] Cordts M, Omran M, Ramos S, et al. The cityscapes dataset for semantic urban scene understanding. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 3213–3223.
    [17] Lee CH, Liu ZW, Wu LY, et al. MaskGAN: Towards diverse and interactive facial image manipulation. Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 5548–5557.
    [18] Liu Y, Chu LT, Chen GW, et al. Paddleseg: A high-efficient development toolkit for image segmentation. arXiv: 2101.06175, 2021.
    [19] Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481–2495. [doi: 10.1109/TPAMI.2016.2644615
    [20] Mazzini D. Guided upsampling network for real-time semantic segmentation. Proceedings of the British Machine Vision Conference. Newcastle: BMVA Press, 2018. 117.
    [21] Artacho B, Savakis A. Waterfall atrous spatial pooling architecture for efficient semantic segmentation. Sensors, 2019, 19(24): 5361. [doi: 10.3390/s19245361
    [22] Lin GS, Milan A, Shen CH, et al. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 5168–5177.
    [23] Bai X, Zhou J. Parallel global convolutional network for semantic image segmentation. IET Image Processing, 2021, 15(1): 252–259. [doi: 10.1049/ipr2.12025
    [24] Yang MK, Yu K, Zhang C, et al. DenseASPP for semantic segmentation in street scenes. Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 3684–3692.
    [25] Bai X, Zhou J. Efficient semantic segmentation using multi-path decoder. Applied Sciences, 2020, 10(18): 6386. [doi: 10.3390/app10186386
    [26] Wang PQ, Chen PF, Yuan Y, et al. Understanding convolution for semantic segmentation. Proceedings of 2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe: IEEE, 2018. 1451–1460.
    [27] Yu CQ, Wang JB, Peng C, et al. BiSeNet: Bilateral segmentation network for real-time semantic segmentation. Proceedings of the 15th European Conference on Computer Vision. Munich: Springer, 2018. 334–349.
    [28] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015. 234–241.
    [29] Luo L, Xue DY, Feng XL. EHANet: An effective hierarchical aggregation network for face parsing. Applied Sciences, 2020, 10(9): 3135. [doi: 10.3390/app10093135
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

张富财,许建龙,包晓安.基于稠密扩张卷积的图像语义分割模型.计算机系统应用,2022,31(3):19-29

复制
分享
文章指标
  • 点击次数:993
  • 下载次数: 8167
  • HTML阅读次数: 1882
  • 引用次数: 0
历史
  • 收稿日期:2021-05-23
  • 最后修改日期:2021-06-21
  • 在线发布日期: 2022-01-24
文章二维码
您是第11418545位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号