[3] C ZHU, H ZHOU, R WANG. A novel hierarchical method of ship detection from spaceborne opticalImage based on shape and texture features. IEEE Transactions on Geoscience and Remote Sensing, 48, 3446-3456(2010).

[5] S QI, M JIE, L JIN. Unsupervised ship detection based on saliency and S-HOG descriptor from optical satellite images. IEEE Geoscience & Remote Sensing Letters, 12, 1451-1455(2015).

[6] J TANG, C DENG, G B HUANG. Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learningmachine. IEEE Transactions on Geoscience & Remote Sensing, 53, 1174-1185(2014).

[7] Y DONG, B DU, L ZHANG. Target detection based on random forest metric learning. IEEE Journal of Selected Topics in Applied Earth Observations& Remote Sensing, 8, 1830-1838(2017).

[9] [9] KRIZHEVSKY A, SUTSKEVER I, HINTON G. Image classification with deep convolutional neural wks[C]. NIPS, Curran Associates Inc, 2012.

[11] [11] GIRSHICK R. Fast RCNN[C]. Proceedings of the IEEE International Conference on Computer Vision, Los Alamitos: IEEE Computer Society Press, 2015: 14401448.

[12] [12] REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: towardsrealtime object detection with region proposal wks[C]. Proceedings of the 28th International Conference on NeuralInfmation Processing Systems, Cambridge: MIT Press, 2015, 1: 9199.

[13] [13] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, realtime object detection[C]. Proceedings of the IEEEInternational Conference on Computer Vision, Los Alamitos: IEEE Computer Society Press, 2016: 779788.

[14] [14] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]. Proceedings of the 2017 IEEE Conference on Computer Vision Pattern Recognition(CVPR), Hawaii: IEEE, 2017: 65176525.

[15] [15] REDMON J, FARHADI A. YOLOv3: An incremental improvement[J]. arXiv: 1804.02767, 2018.

[16] [16] LIU W, ANGUELOV D, ERHAN D, et al.SSD: Single shot multibox detect[C] Proceedings of the European Conference on Computer Vision.Amsterdam: Springer International Publishing, 2016: 2127.

[17] [17] FU C, LIU W, RANGAA, et al. DSSD: Deconvolutional single shot detect[J]. arXiv: 1701.06659, 2017.

[18] [18] CAO G M, XIE X M, YANG W Z, et al. Featurefused SSD: fastdetection f small objects[J]. arXiv: 1709.05054, 2017.

[23] [23] LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyra wks f object detection[C]. Proceedings of the IEEE Conference on Computer Vision Pattern Recognition, Hawaii: IEEE, 2017: 936944.

[24] [24] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss f dense object detection[C]. 2017 IEEE international conference on computer vision(ICCV), October 2229, Venice, Italy, New Yk: IEEE, 2017: 29802988.

[25] M EVERINGHAM, S M A ESLAMI, L V GOOL. The pascal visual object classes challenge:a retrospective. International Journal of Computer Vision, 111, 98-136(2015).

[26] [26] LIN T Y, MAIRE M, BELONGIE S, et al.Microsoft coco: Common objects in context[C]. Proceedings of the EuropeanConference on Computer Vision, Zurich: Springer International Publishing, 2014: 740755.

[27] Z WANG, K CRAMMER, S VUCETIC. Breaking the curse of kernelization:budgeted stochastic gradient descent for large-scale SVM training. Journal of Machine Learning Research, 13, 3103-3131(2012).