Abstract
Not safe for work content automatic detection is a serious challenge for social media due to overwhelming growth of uploaded images, gifs and videos. This paper focuses on shocking images automatic detection by convolutional neural networks. It was considered that the correct recognition of the shocking class is more important than the non-shocking one. Binary classification by a convolutional network that training during operation has been used as a baseline solution. However, this solution has two drawbacks: the network highlights incorrect features of non-shocking images (infinite class) and tends to forget rare subclasses of shocking images, which is unacceptable. To eliminate the first drawback, we approach this problem as a one-class classification with having in mind that a “non-shocking” image can be defined only via contradiction with a shocking one. This method is based on using sparse autoencoders build on top of a pretrained convolutional neural network and is not trained during operation. To eliminate the second drawback, we memorized vectors of images that were incorrectly classified during operation. A trained siamese network during the prediction is used to search for similar images in the database. In the case of an incorrect prediction by the combined model, vectors of images are added to the database and the siamese network is trained on them. This method allows you to minimize the number of errors in rare subclasses identified only during the operation phase of the model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Anderson, C.A., Berkowitz, L., Donnerstein, E., Huesmann, L.R., Johnson, J., Linz, D.: The influence of media violence on youth. Psychol. Sci. Public Interest 4, 81–110 (2003)
Bourlard, H., Kamp, Y.: Auto-association by multilayer perceptrons and singular value decomposition. Biol. Cybern. 59(4–5), 291–294 (1988)
Bushman, B.J., Huesmann, L.R.: Short-term and long-term effects of violent media on aggression in children and adults. Arch. Pediatr. Adolesc. Med. 160, 348–352 (2006)
Dubberley, S., Griffin, E., Bal, H.M.: Making secondary trauma a primary issue: a study of eyewitness media and vicarious trauma on the digital frontline (2015). http://eyewitnessmediahub.com/uploads/browser/files/Trauma%20Report.pdf. Accessed 15 Jan 2020
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Khan, S.S., Madden, M.G.: A survey of recent trends in one class classification. In: Irish Conference on Artificial Intelligence and Cognitive Science, pp. 188–197. Springer, Heidelberg (2009)
Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In ICML Deep Learning Workshop, vol. 2 (2015)
Li, B., Xiong, W., Wu, O., Hu, W., Maybank, S., Yan, S.: Horror image recognition based on context-aware multi-instance learning. IEEE Trans. Image Process. 24(12), 5193–5205 (2015)
Luxton, D.D., June, J.D., Fairall, J.M.: Social media and suicide: a public health perspective. Am. J. Public Health 102(S2), S195–S200 (2012)
Poultney, C., Chopra, S., Cun, Y.L.: Efficient learning of sparse representations with an energy-based model. In: Advances in neural information processing systems, pp. 1137–1144 (2007)
Schlkopf, B., Williamson, R.C., Smola, A.J., Shawe-Taylor, J., Platt, J.C.: Support vector method for novelty detection. In: Advances in Neural Information Processing Systems, pp. 582–588 (2000)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Wang, D., Zhang, Z., Wang, W., Wang, L., Tan, T.: Baseline results for violence detection in still images. In: IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, pp. 54–57 (2012)
Zampoglou, M., Papadopoulos, S., Kompatsiaris, Y., Spangenberg, J. A WebBased Service for Disturbing Image Detection. In: International Conference on Multimedia Modeling, pp. 438–441, Springer, Cham (2017)
Zheng, L., Zhao, Y., Wang, S., Wang, J., Tian, Q.: Good practice in CNN feature transfer (2016). arXiv preprint arXiv:1604.00133
Acknowledgments
This work was financially supported by the Government of the Russian Federation (Grant 08-08). The authors would like to thank Aleksey Artamonov for his constructive comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gulyaev, P., Filchenkov, A. (2020). Detection of Shocking Images as One-Class Classification Using Convolutional and Siamese Neural Networks. In: Iliadis, L., Angelov, P., Jayne, C., Pimenidis, E. (eds) Proceedings of the 21st EANN (Engineering Applications of Neural Networks) 2020 Conference. EANN 2020. Proceedings of the International Neural Networks Society, vol 2. Springer, Cham. https://doi.org/10.1007/978-3-030-48791-1_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-48791-1_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-48790-4
Online ISBN: 978-3-030-48791-1
eBook Packages: Computer ScienceComputer Science (R0)