In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. Gatys, L., Ecker, A.S., Bethge, M.: Texture synthesis using convolutional neural networks.
Mathieu, M., Zhao, J., Sprechmann, P., Ramesh, A., LeCun, Y.: Disentangling factors of variation in deep representations using adversarial training. Zheng, Y., Zhang, X., Wang, F., Cao, T., Sun, M., Wang, X.: Detection of people with camouflage pattern via dense deconvolution network. 16(3), 555–563 (2020)Īlfimtsev, A.N., Sakulin, S.A., Loktev, D.A., Kovalenko, A.O., Devyatkov, V.V.: Hostis humani ET mashinae: adversarial camouflage generation. Yang, X., et al.: Research on extraction and reproduction of deformation camouflage spots based on generative adversarial network model. Yang, X., Xu, W.D., Jia, Q., Li, L.: Research on digital camouflage pattern generation algorithm based on adversarial autoencoder network. Zhuo, L., Chen, X.Q., Xie, Z.P., Jiang, X.J., Bi, D.K.: Simulation learning method for discovery of camouflage targets based on deep neural networks. Experiments show that the proposed method can generate digital camouflage images in different seasons and successfully implement an adversarial attack on the classification model. To counter the detection of the classification models, we design a category reordering function to mislead the classification result of the classification model. When the environment changes, our model can generate digital camouflage images based on the original environment content and the corresponding digital camouflage style, without obtaining the current environment image. We present a digital camouflage generation model based on disentangled representation, which can decompose images into a content space and a style space, thereby recombining the current content of the environment image with different digital camouflage styles. When the environment changes, generated camouflage images may be detected by neural network classification models. Traditional digital camouflage generation methods must regenerate camouflage images according to the current environment. Digital camouflage is the most common and effective means to combat military reconnaissance.