Abstract
Convolution neural network (CNN) achieves outstanding results in single-label image classification task. However, due to the complex underlying object layout and insufficient multi-label training images, it is still an open problem that how CNN better handle multi-label images. In this work, we proposes an improved deep CNN model with Adversarial Net which can extract features of objects at different scales in multi-label images by spatial pyramid pooling. In model training, we first transfer the parameters pre-trained on ImageNet to our model, then train an Adversarial Network to generates examples with occlusions and combine it with our model, which make our model invariant to occlusions. Experimental results on Pascal VOC 2012 multi-label image dataset demonstrate the superiority of the proposed approach over many state-of-the-arts approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zan, W., Tsim, Y.C., Yeung, W.S., Chan, K.C.: Probabilistic latent semantic analyses (plsa) in bibliometric analysis for technology forecasting. J. Technol. Manag. Innov. 2(1), 11–24 (2007)
Li, Z., Shi, Z., Zhao, W., Li, Z., Tang, Z.: Learning semantic concepts from image database with hybrid generative/discriminative approach. Eng. Appl. Artif. Intell. 26(9), 2143–2152 (2013)
Dong, J., Xia, W., Chen, Q., Feng, J., Huang, Z., Yan, S.: Subcategory-aware object classification. In: Proceedings of CVPR, pp. 827–834 (2013)
Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: Factors of transferability for a generic convnet representation. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1790–1802 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904–1916 (2015)
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., Lecun, Y.: Overfeat: Integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)
Wei, Y., et al.: HCP: a flexible CNN framework for multi-label image classification. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1901–1907 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2014)
Wang, X., Shrivastava, A., Gupta, A.: A-fast-RCNN: hard positive generation via adversary for object detection. In: Proceedings of the CVPR, pp. 21–26 (2017)
Duygulu, P., Freitas, N.D., Barnard, K., Forsyth, D.A.: Object recognition as machine translation. In: Proceedings of the ECCV, pp. 97–112 (2002)
Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88(2), 303–338 (2010)
Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the CVPR, pp. 1717–1724 (2014)
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Nos. 61663004), the Guangxi Natural Science Foundation (Nos. 2016GXNSFAA380146, 2017GXNSFAA198365), the Research Fund of Guangxi Key Lab of Multi-source Information Mining and Security (16-A-03-02), the Guangxi Special Project of Science and Technology Base and Talents (AD16380008) and the Guangxi Collaborative Innovation Center of Multi-source Information Integration and Intelligent Processing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Zhou, T., Li, Z., Zhang, C., Lin, L. (2018). An Improved Convolutional Neural Network Model with Adversarial Net for Multi-label Image Classification. In: Geng, X., Kang, BH. (eds) PRICAI 2018: Trends in Artificial Intelligence. PRICAI 2018. Lecture Notes in Computer Science(), vol 11013. Springer, Cham. https://doi.org/10.1007/978-3-319-97310-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-97310-4_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97309-8
Online ISBN: 978-3-319-97310-4
eBook Packages: Computer ScienceComputer Science (R0)