基于改进的MoCo的遥感图像目标检测

摘要/Abstract

摘要： 卫星遥感图像的智能化处理存在着处理标注时标准不统一、数据分布不均匀的问题，导致有效样本不多、目标检测效果较差的现象。针对这种现象，提出一种基于MoCo无监督对比学习模型的目标检测算法，目标检测的框架采用以ResNet50为骨干网络的YOLOv5，使用对比学习得到的ResNet50的权重作为固定值不进行梯度迭代参与YOLOv5下游的检测任务训练。对比学习实验在AID数据集上进行，改进的MoCo v2的top-1精度最高达到95.888%。在下游的检测任务中，使用的是TGRS-HRRSD数据集，改进MoCo v2的预训练权重的mAP@.5:.95精度达到67.8%，较不使用预训练权重提高了5.6个百分点。结果证明改进的MoCo对比学习模型的有效性，在对比学习之后的下游检测任务中，检测精度也有所提高。

关键词: 无监督对比学习, 遥感图像检测, 注意力机制, YOLOv5

Abstract: In the intelligent processing of satellite remote sensing images, there are some problems such as inconsistent standards and uneven data distribution, resulting in few effective samples and poor object detection effect. Aiming at this phenomenon, an object detection algorithm based on MoCo unsupervised contrast learning model is proposed. The framework of object detection adopts YOLOv5 with ResNet50 as the backbone network, and the weight of ResNet50 obtained by contrastive learning is used as a fixed value to participate in the detection task training of YOLOv5 downstream without gradient iteration. The contrastive learning experiment is carried out on AID Dataset, and the top-1 accuracy of the improved MoCo v2 is 95.888%. In the downstream detection task, using the TGRS-HRRSD Dataset, the accuracy of mAP@.5:.95 with the improved MoCo v2 pre-training weight is 67.8%, which is 5.6 percentage points higher than that without the pre-training weight. The results show that the improved MoCo comparative learning model is effective, and the detection accuracy is also improved in the downstream detection tasks after the comparative learning.

Key words: unsupervised contrastive learning, remote sensing image detection, attention, YOLOv5

焦新泉, 李睿康, 陈建军. 基于改进的MoCo的遥感图像目标检测[J]. 计算机与现代化, 2022, 0(12): 88-94.

JIAO Xin-quan, LI Rui-kang, CHEN Jian-jun. Remote Sensing Image Object Detection Based on Improved MoCo[J]. Computer and Modernization, 2022, 0(12): 88-94.

参考文献［37］

［1］	ZHANG X, LIU L Y, CHEN X D, et al. A novel multitemporal cloud and cloud shadow detection method using the integrated cloud z-scores model［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019,12(1):123-134.
［2］	GUO J H, YANG J Y, YUE H J, et al. CDnetV2: CNN-based cloud detection for remote sensing imagery with cloud-snow coexistence［J］. IEEE Transactions on Geoscience and Remote Sensing, 2021,59(1):700-713.
［3］	HU J, SHEN L, SUN G. Squeeze-and-excitation networks［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018:7132-7141.
［4］	WANG Q, WU B, ZHU P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020:11531-11539.
［5］	XIA G S, HU J W, HU F, et al. AID: A benchmark data set for performance evaluation of aerial scene classification［J］. IEEE Transactions on Geoscience and Remote Sensing, 2017,55(7):3965-3981.
［6］	ZHANG Y L, YUAN Y, FENG Y C, et al. Hierarchical and robust convolutional neural network for very high-resolution remote sensing object detection［J］. IEEE Transactions on Geoscience and Remote Sensing, 2019,57(8):5535-5548.
［7］	CHEN J, WAN L, ZHU J R, et al. Multi-scale spatial and channel-wise attention for improving object detection in remote sensing imagery［J］. IEEE Geoscience and Remote Sensing Letters, 2020,17(4):681-685.
［8］	TAN Q L, LING J, HU J, et al. Vehicle detection in high resolution satellite remote sensing images based on deep learning［J］. IEEE Access, 2020,8:153394-153402.
［9］	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// 2014 IEEE Conference on Computer Vision and Pattern Recognition. 2014:580-587.
［10］	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.
［11］	REDMON J, FARHADI A. YOLOv3: An incremental improvement［J］. arXiv preprint arXiv:1804.02767, 2018.
［12］	BOCHKOVSKIY A, WANG C Y, MARK LIAO H Y. YOLOv4: Optimal speed and accuracy of object detection［J］. arXiv preprint arXiv:2004.10934, 2020.
［13］	LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single ShotMultiBox Detector［C］// 2016 European Conference on Computer Vision. 2016:21-37.
［14］	FU C Y, LIU W, RANGA A, et al. DSSD: Deconvolutional single shot detector［J］. arXiv preprint arXiv:1701.06659, 2017.
［15］	HE K M, ZHANG X, REN S Q, et al. Deep residual learning for image recognition［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:770-778.
［16］	LIN T, DOLLR P, GIRSHICK R, et al. Feature pyramid networks for object detection［C］// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017:936-944.
［17］	LI H, XIONG P, AN J, et al. Pyramid attention network for semantic segmentation［J］. arXiv preprint arXiv:1805.10180, 2018.
［18］	DOSOVITSKIY A, FISCHER P, SPRINGENBERG J T, et al. Discriminative unsupervised feature learning with exemplar convolutional neural networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016,38(9):1734-1747.
［19］	YE M, ZHANG X, YUEN P C, et al. Unsupervised embedding learning via invariant and spreading instance feature［C］// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019:6203-6212. 〖HJ0.27mm〗
［20］	OORD A V D, LI Y, VINYALS O. Representation learning with contrastive predictive coding［J］. arXiv preprint arXiv:1807.03748, 2018.
［21］	HNAFF O J, SRINIVAS A, FAUW J D, et al. Data-efficient image recognition with contrastive predictive coding［C］// Proceedings of the 37th International Conference on Machine Learning. 2020:4182-4192.
［22］	DEVON HJELM R, FEDOROV A, LAVOIE-MARCHILDON S, et al. Learning deep representations by mutual information estimation and maximization［J］. arXiv preprint arXiv:1808.06670, 2018.
［23］	BACHMAN P, HJELM R D, BUCHWALTER W. Learning representations by maximizing mutual information across views［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019:15535-15545.
［24］	WU Z R, XIONG Y J, YU S X, et al. Unsupervised feature learning via non-parametric instance discrimination［C］// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018:3733-3742.
［25］	HE K M, FAN H Q, WU Y X, et al. Momentum contrast for unsupervised visual representation learning［C］// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020:9726-9735.
［26］	CHEN X L, FAN H Q, GIRSHICK R, et al. Improved baselines with momentum contrastive learning［J］. arXiv preprint arXiv:2003.04297, 2020.
［27］	CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations［J］. arXiv preprint arXiv:2002.05709, 2020.
［28］	XIE E, DING J, WANG W, et al.DetCo: Unsupervised contrastive learning for object detection［C］// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 2021:8372-8381.
［29］	LI Y, ZHANG Y, HUANG X, et al. Deep networks under scene-level supervision for multi-class geospatial object detection from remote sensing images［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2018,146:182-196.
［30］	LI Y, CHEN W, ZHANG Y, et al. Accurate cloud detection in high-resolution remote sensing imagery by weakly supervised deep learning［J］. Remote Sensing of Environment, 2020. DOI:10.1016/j.rse.2020.112045.
［31］	LI Y, KONG D, ZHANG Y, et al. Robust deep alignment network with remote sensing knowledge graph for zero-shot and generalized zero-shot remote sensing image scene classification［J］. ISPRS Journal of Photogrammetry and Remote Sensing, 2021,179:145-158.
［32］	GUTMANN M, HYVRINEN A. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models［J］. Journal of Machine Learning Research, 2010,9:297-304.
［33］	CARON M, BOJANOWSKI P, JOULIN A, et al. Deepclustering for unsupervised learning of visual features［C］// 2018 European Conference on Computer Vision. 2018:139-156.
［34］	CARON M, MISRA I, MAIRAL J, et al. Unsupervised learning of visual features by contrasting cluster assignments［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020:9912-9924.
［35］	JIANG Z, VON N K, LOISEL J, et al.ArcticNet: A deep learning solution to classify arctic wetlands［J］. arXiv preprint arXiv:1906.00133, 2019.
［36］	LU X, ZHANG Y, YUAN Y, et al. Gated and axis-concentrated localization network for remote sensing object detection［J］. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(1):179-192.
［37］	韩伟. 基于深度神经网络的高分辨率遥感影像弱小目标检测［D］. 武汉:中国地质大学, 2021.

[1]	栗伟松, 汤敏芳, 何征岭, 王鹏, 杜利东, 方震, 陈贤祥. 基于自注意力机制和单导联心电信号的自动睡眠分期算法#br#[J]. 计算机与现代化, 2022, 0(12): 50-59.
[2]	张飙, 王慧贤, 韩冰, . 基于改进YOLOv3的高分辨率遥感图像复合目标检测[J]. 计算机与现代化, 2022, 0(12): 74-80.
[3]	黄忠祥, 李明. ALBERT结合双向网络的文本分类[J]. 计算机与现代化, 2022, 0(10): 8-12.
[4]	于鹏, 陈钰枫, 徐金安, 张玉洁. 基于多任务学习的电子病历实体识别方法[J]. 计算机与现代化, 2022, 0(09): 40-50.
[5]	孟晓龙, . DNeStCount:数据相关的拆分注意力机制的编码器-解码器结构的人群计数方法[J]. 计算机与现代化, 2022, 0(09): 68-77.
[6]	王梦, 张鸿鑫, 刘庆华, 张东. 基于改进YOLOv5的幽门螺杆菌免疫印迹图像识别[J]. 计算机与现代化, 2022, 0(09): 78-84.
[7]	许鸿奎, 张子枫, 卢江坤, 周俊杰, 胡文烨, 姜彤彤. 混合CTC/Attention模型在普通话识别中的应用[J]. 计算机与现代化, 2022, 0(08): 1-6.
[8]	周慧, 徐名海, 许晓东. 基于Attention-BIGRU-CRF的中文分词模型[J]. 计算机与现代化, 2022, 0(08): 7-12.
[9]	冯申, 於跃成, 张宗海. 结合动态多类信息的兴趣点推荐[J]. 计算机与现代化, 2022, 0(08): 57-64.
[10]	任秋霖, 任德均, 李鑫, 闫宗一, 曹林杰, 唐洪. 基于卷积自编码器的医用玻璃瓶口缺陷检测方法[J]. 计算机与现代化, 2022, 0(08): 114-120.
[11]	孙弘扬, 王尚. 基于残差门控循环卷积和注意力机制的端到端光学乐谱识别方法[J]. 计算机与现代化, 2022, 0(07): 85-90.
[12]	贺雨霞, 曹国. 基于改进注意力网络的转炉炼钢状态判别[J]. 计算机与现代化, 2022, 0(07): 97-102.
[13]	饶海兵, 朱苏磊, 杨春夏. 基于空时特征融合和注意力机制的网络入侵检测模型[J]. 计算机与现代化, 2022, 0(06): 116-121.
[14]	张宗海, 於跃成, 冯申. 融合三重注意力和评论评分的深度推荐算法[J]. 计算机与现代化, 2022, 0(05): 1-9.
[15]	王柯阳, 张铫, 李科闻, 张保谦, 李江, 任杰文. 基于Attention-LSTM的CNC刀具破损在线检测系统[J]. 计算机与现代化, 2022, 0(05): 68-74.