Abstract
Deep learning is one of the essential technologies for remote sensing tasks, which heavily depends on the quantity of training data. However, it is difficult to obtain or label the remotely sensed images in their non-cooperative imaging mode. Data augmentation is a viable solution to this issue, but most of the current data augmentation methods are task specific or dataset specific, which are not as applicable as a generalized solution for the remotely sensed images. In this paper, we propose a category-oriented adversarial data augmentation method using statistic similarity cross categories, which formulates the common appearance-based statistic factors in the object detection into a combination index, to depict the statistic similarity between different categories and to generate new adversarial samples between similar categories with more reliable physical significance. Experimental results demonstrated that, taking the most advanced RT method as a baseline, the total mAP can be increased by 2.0% on the DOTA dataset for the object detection task by using our proposed method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Xia, G.S., Bai, X., Ding, J., et al.: DOTA: A large-scale dataset for object detection in aerial images. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3974–3983 (2018)
LeCun, Y., Bottou, L., Bengio, Y., et al.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Wan, L., Zeiler, M., Zhang, S., et al.: Regularization of Neural Networks using Dropconnect. In: International Conference on Machine Learning. ICLR, pp. 1058–1066 (2013)
Zagoruyko, S., Komodakis, N.: Wide Residual Networks. British Machine Vision Conference (2016)
Zhong, Z., Zheng, L., Kang, G., et al.: Random erasing data augmentation. In: AAAI Conference on Artificial Intelligence. 34(07), 13001–13008 (2020)
Lemley, J., Bazrafkan, S., Corcoran, P.: Smart augmentation learning an optimal data augmentation strategy. IEEE Access 5, 5858–5869 (2017)
Tran, T., Pham, T., Carneiro, G., et al.: A bayesian data augmentation approach for learning deep models. In: Advances in Neural Information Processing Systems, pp. 2794–2803 (2017)
Cubuk, E.D., Zoph, B., Mane, D., et al.: Autoaugment: Learning Augmentation Policies from Data. arXiv preprint arXiv:1805.09501 (2018)
Wang, Z., She, Q., Ward, T.E.: Generative adversarial networks in computer vision: a survey and taxonomy. ACM Computing Surveys (CSUR) 54(2), 1–38 (2021)
Goodfellow, I., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. Advances in Neural Information Processing Systems, NIPS, p. 27 (2014)
Zhu, J.Y., Park, T., Isola, P., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision, ICCV, pp. 2223–2232 (2017)
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694–711. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46475-6_43
Isola, P., Zhu, J.Y., Zhou, T., et al.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 1125–1134 (2017)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 770–778 (2016)
Ding, J., Xue, N., Long, Y., et al.: Learning roi transformer for oriented object detection in aerial images. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 2849–2858 (2019)
Li, Z., Peng, C., Yu, G., et al.: Light-head R-CNN: In: Defense of Two-stage Object Detector. arXiv preprint arXiv:1711.07264 (2017)
Ding, X., Guo, Y., Ding, G., et al.: Acnet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. In: IEEE/CVF International Conference on Computer Vision. ICCV, pp. 1911–1920 (2019)
Kong, T., Sun, F., Yao, A., et al.: Ron: reverse connection with objectness prior networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 5936–5944 (2017)
Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: IEEE Conference on Computer Vision and Pattern Recognition. CVPR, pp. 7132–7141 (2018)
Chen, L.C., Papandreou, G., Kokkinos, I., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Analysis Machine Intelligence 40(4), 834–848, (2017)
Lin, T.Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. IEEE Trans. Pattern Analysis Machine Intelligence pp. 2999–3007 (2017)
Jiang, Y., Zhu, X., Wang, X., et al.: R2CNN: rotational region cnn for orientation robust scene text detection. arXiv preprint arXiv:1706.09579 (2017)
Ma, J., Shao, W., Ye, H., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Transactions on Multimedia 20(11), 3111–3122 (2018)
Dai, J., Qi, H., Xiong, Y., et al.: Deformable convolutional networks. In: IEEE International Conference on Computer Vision. ICCV, pp. 764–773 (2017)
Yang, X., et al.: Automatic ship detection in remote sensing images from google earth of complex scenes based on multiscale rotation dense feature pyramid networks. Remote Sensing 10(1), 132 (2018)
Yang, X., Sun, H., Sun, X., Yan, M., Guo, Z., Fu, K.: Position detection and direction prediction for arbitrary-oriented ships via multiscale rotation region convolutional neural network. IEEE Access 6, 50839–50849 (2018)
Mariani, G., Scheidegger, F., Istrate, R., et al.: Bagan: Data Augmentation with Balancing GAN. arXiv preprint arXiv:1803.09655 (2018)
Zhao, S., Liu, Z., Lin, J., et al.: Differentiable augmentation for data-efficient GAN training. Adv. Neural. Inf. Process. Syst. 33, 7559–7570 (2020)
Jiang, L., Dai, B., Wu, W., et al.: Deceive D: Adaptive pseudo augmentation for GAN training with limited data. Advances in Neural Inf. Processing Systems 34, 2165521667 (2021)
Schindler, K., Suter, D.: Object detection by global contour shape. Pattern Recogn. 41(12), 3736–3748 (2008)
Zhang, H., Xu, Z., Han, X., et al.: Refining FFT-based heatmap for the detection of cluster distributed targets in satellite images, British Machine Vision Conference (2021)
Shmelkov, K., Schmid, C., Alahari, K.: How good Is my GAN? In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 218–234. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01216-8_14
Wang, H., Suter, D., Schindler, K.: Effective appearance model and similarity measure for particle filtering and visual tracking. In: European Conference on Computer Vision. Springer, Berlin, Heidelberg, pp. 606–618 (2006). https://doi.org/10.1007/11744078_47
Bell, S., Bala, K.: Learning visual similarity for product design with convolutional neural networks. ACM Trans. Graphics (TOG) 34(4), 1–10 (2015)
Siggelkow, S., Schael, M., Burkhardt, H.: SIMBA—search IMages by appearance. In: Joint Pattern Recognition Symposium. Springer, Berlin, Heidelberg, pp. 9-16 (2001). https://doi.org/10.1007/3-540-45404-7_2
Acknowledgement
This work was supported in part by the National Nature Science Foundation (41971294), China Postdoctoral Science Foundation (2020M680560) and Cross-Media Intelligent Technology Project of BNRist (BNR2019TD01022) of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, H., Leng, W., Han, X., Sun, W. (2022). Category-Oriented Adversarial Data Augmentation via Statistic Similarity for Satellite Images. In: Yu, S., et al. Pattern Recognition and Computer Vision. PRCV 2022. Lecture Notes in Computer Science, vol 13536. Springer, Cham. https://doi.org/10.1007/978-3-031-18913-5_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-18913-5_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18912-8
Online ISBN: 978-3-031-18913-5
eBook Packages: Computer ScienceComputer Science (R0)