您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (2): 99-106.doi: 10.6040/j.issn.1672-3961.0.2021.329

• • 上一篇    

基于弱监督和半监督学习的红外舰船分割方法

尹旭1,刘兆英1,张婷1*,李玉鑑1,2   

  1. 1. 北京工业大学信息学部, 北京 100124;2. 桂林电子科技大学人工智能学院, 广西 桂林 541004
  • 发布日期:2022-04-20
  • 作者简介:尹旭(1996— ),男,宁夏中宁人,硕士研究生,主要研究方向为人工智能. E-mail:yinxubjut@163.com. *通信作者简介:张婷(1986— ),女,河南郑州人,讲师,博士,主要研究方向为人工智能. E-mail:zhangting@bjut.edu.cn
  • 基金资助:
    国家自然科学基金项目(61906005,61806013,61876010);北京市教育委员会科技计划一般项目(KM202110005028);北京工业大学交叉科学研究院资助项目(2021020101);北京工业大学国际科研合作种子基金资助项目(2021A01)

Infrared ship segmentation method based on weakly-supervised and semi-supervised learning

YIN Xu1, LIU Zhaoying1, ZHANG Ting1*, LI Yujian1,2   

  1. 1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China;
    2. School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin 541004, Guangxi, China
  • Published:2022-04-20

PDF (PC)

171

摘要： 为降低获取像素级标签的成本,提出一种基于弱监督和半监督学习的红外舰船分割方法,在残差网络(residual network, ResNet)的基础上,设计一个自适应定位模块,并使用相似损失、前景损失和背景损失训练自适应定位模块,生成舰船定位图;利用少量像素级标签数据和大量定位图数据交替训练显著性网络生成显著图;用条件随机场优化显著图,并结合图像级标签生成伪标签图像,使用伪标签图像训练分割网络,得到红外舰船的分割结果。在红外舰船数据集上的平均交并比为71.18%,与当前其他先进方法进行对比,平均交并比提高了9.47%,试验结果表明自适应定位模块能够有效定位红外舰船,交替训练方法可以使红外舰船的边缘更准确。

关键词: 红外舰船, 语义分割, 弱监督学习, 半监督学习, 卷积神经网络

中图分类号: 

  • TP3
[1] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2015: 3431-3440.
[2] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C] //Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham, Switzerland: Springer, 2015: 234-241.
[3] BADRINARAYANAN V, KENDALL A, CIPOLLA R. Segnet: a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481-2495.
[4] LIN G, MILAN A, SHEN C, et al. Refinenet: multi-path refinement networks for high-resolution semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017: 1925-1934.
[5] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4): 834-848.
[6] ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017: 2881-2890.
[7] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C] //Proceedings of the European Conference on Computer Vision. Cham, Switzerland: Spri-nger, 2018: 801-818.
[8] 陈倩. 基于局部区域生长和Faster R-CNN的弱监督图像语义分割[D].合肥: 安徽大学, 2020. CHEN Qian. Weakly supervised image semantic segmentation based on local region growth and faster R-CNN[D]. Hefei: Anhui University, 2020.
[9] ZHOU B, KHOSLA A, LAPEDRIZA A, et al. Learning deep features for discriminative localization[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016: 2921-2929.
[10] SINGH K K, LEE Y J. Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization[C] //Proceedings of the 2017 IEEE International Conference on Computer Vision. New York, USA: IEEE, 2017: 3544-3553.
[11] WEI Y, FENG J, LIANG X, et al. Object region mining with adversarial erasing: a simple classification to semantic segmentation approach[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017: 1568-1576.
[12] MAI J, YANG M, LUO W. Erasing integrated learning: a simple yet effective approach for weakly supervised object localization[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2020: 8766-8775.
[13] ZHANG X, WEI Y, FENG J, et al. Adversarial complementary learning for weakly supervised object localization[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 1325-1334.
[14] HOU Q, JIANG P T, WEI Y, et al. Self-erasing network for integral object attention[J]. Advances in Neural Information Processing Systems, 2018, 31: 549-559.
[15] KIM D, CHO D, YOO D, et al. Two-phase learning for weakly supervised object localization[C] //Proceedings of the IEEE International Conference on Computer Vision. New York, USA: IEEE, 2017: 3534-3543
[16] WANG X, SHRIVASTAVA A, GUPTA A. A-fast-rcnn: hard positive generation via adversary for object detection[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2017: 2606-2615.
[17] WEI Y, XIAO H, SHI H, et al. Revisiting dilated convolution: a simple approach for weakly- and semi-supervised semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 7268-7277.
[18] FAN J, ZHANG Z, TAN T, et al. Cian: cross-image affinity net for weakly supervised semantic segmentation[C] //Proceedings of the AAAI Conference on Arti-ficial Intelligence. Palo Alto, USA: AAAI, 2020, 10762-10769.
[19] FAN R, HOU Q, CHENG M M, et al. Associating inter-image salient instances for weakly supervised semantic segmentation[C] //Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 367-383.
[20] KOLESNIKOV A, LAMPERT C H. Seed, expand and constrain: three principles for weakly-supervised image segmentation[C] //Proceedings of the European Conference on Computer Vision. Cham, Switzerland: Springer, 2016: 695-711.
[21] HUANG Z, WANG X, WANG J, et al. Weakly-supervised semantic segmentation network with deep seeded region growing[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 7014-7023.
[22] WANG X, YOU S, LI X, et al. Weakly-supervised semantic segmentation by iteratively mining common object features[C] //Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 1354-1362.
[23] AHN J, KWAK S. Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2018: 4981-4990.
[24] SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-cam: visual explanations from deep networks via gradient-based localization[C] //Proceedings of the IEEE International Conference on Computer Vision. New York, USA: IEEE, 2017: 618-626.
[25] SOULY N, SPAMPINATO C, SHAH M. Semi supervised semantic segmentation using generative adversarial network[C] //Proceedings of the IEEE International Conference on Computer Vision. New York, USA: IEEE, 2017: 5688-5696.
[26] AI J, CHEN S, DENG P, et al. CycleGANs for semi-supervised defects segmentation[C] //Proceedings of the 2020 International Conference on Sensing, Measurement & Data Analytics in the Era of Artificial Intel-ligence(ICSMD). Xi'an, China: IEEE, 2020: 611-616.
[27] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016: 770-778.
[28] WU Z, SU L, HUANG Q. Cascaded partial decoder for fast and accurate salient object detection[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2019: 3907-3916.
[29] KINGMA D, BA J. Adam: a method for stochastic optimization[C] //Proceedings of the 3rd International Conference on Learning Representations. CA, USA: ICLR, 2015: 1-13.
[30] KRÄHENB(¨overU)HL P, KOLTUN V. Efficient inference in fully connected crfs with gaussian edge potentials[J]. Advances in Neural Information Processing Systems, 2011, 24(24): 109-117.
[1] 龚楷伦,翟婷婷,唐鸿成. 一种面向多标签分类的在线主动学习算法[J]. 山东大学学报 (工学版), 2022, 52(2): 80-88.
[2] 王心哲,邓棋文,王际潮,范剑超. 深度语义分割MRF模型的海洋筏式养殖信息提取[J]. 山东大学学报 (工学版), 2022, 52(2): 89-98.
[3] 张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.
[4] 朱恒东, 马盈仓, 代雪珍. 自适应半监督邻域聚类算法[J]. 山东大学学报 (工学版), 2021, 51(4): 24-34.
[5] 陶亮,刘宝宁,梁玮. 基于CNN-LSTM 混合模型的心律失常自动检测[J]. 山东大学学报 (工学版), 2021, 51(3): 30-36.
[6] 曹春红,段鸿轩,曹玲,张乐乐,胡凯,肖芬. 基于多级特征级联的遥感图像实时语义分割[J]. 山东大学学报 (工学版), 2021, 51(2): 19-25.
[7] 廖锦萍,莫毓昌,YAN Ke. 基于C-LSTM的短期用电预测模型和应用[J]. 山东大学学报 (工学版), 2021, 51(2): 90-97.
[8] 廖南星,周世斌,张国鹏,程德强. 基于类激活映射-注意力机制的图像描述方法[J]. 山东大学学报 (工学版), 2020, 50(4): 28-34.
[9] 李春阳,李楠,冯涛,王朱贺,马靖凯. 基于深度学习的洗衣机异常音检测[J]. 山东大学学报 (工学版), 2020, 50(2): 108-117.
[10] 宋士奇,朴燕,蒋泽新. 基于改进YOLOv3的复杂场景车辆分类与跟踪[J]. 山东大学学报 (工学版), 2020, 50(2): 27-33.
[11] 蔡国永,林强,任凯琪. 基于域对抗网络和BERT的跨领域文本情感分析[J]. 山东大学学报 (工学版), 2020, 50(1): 1-7,20.
[12] 周杨浩,刘一帆,李瑮. 一种自动读取指针式仪表读数的方法[J]. 山东大学学报 (工学版), 2019, 49(4): 1-7.
[13] 侯霄雄,许新征,朱炯,郭燕燕. 基于AlexNet和集成分类器的乳腺癌计算机辅助诊断方法[J]. 山东大学学报 (工学版), 2019, 49(2): 74-79.
[14] 权稳稳,林明星. CNN特征与BOF相融合的水下目标识别算法[J]. 山东大学学报 (工学版), 2019, 49(1): 107-113.
[15] 梁蒙蒙,周涛,夏勇,张飞飞,杨健. 基于PSO-ConvK卷积神经网络的肺部肿瘤图像识别[J]. 山东大学学报 (工学版), 2018, 48(5): 77-84.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发