Learning Inverse Mapping by AutoEncoder Based Generative Adversarial Nets
The inverse mapping of GANs’ (Generative Adversarial Nets) generator has a great potential value. Hence, some works have been developed to construct the inverse function of generator by directly learning or adversarial learning. While the results are encouraging, the problem is highly challenging and the existing ways of training inverse models of GANs have many disadvantages, such as hard to train or poor performance. Due to these reasons, we propose a new approach based on using inverse generator (IG) model as encoder and pre-trained generator (G) as decoder of an AutoEncoder network to train the IG model. In the proposed model, the difference between the input and output, which are both the generated image of pre-trained GAN’s generator, of AutoEncoder is directly minimized. The optimizing method can overcome the difficulty in training and inverse model of an non one-to-one function. We also applied the inverse model of GANs’ generators to image searching and translation. The experimental results prove that the proposed approach works better than the traditional approaches in image searching.
KeywordsInverse model GAN AutoEncoder network
This work was supported by the National Science Foundation of China (Grant No. 61375065 and 61625204), partially supported by the State Key Program of National Science Foundation of China (Grant No. 61432012 and 61432014).
- 1.Goodfellow, I.J., Pougetabadie, J., Mirza, M., Xu, B., Wardefarley, D., Ozair, S., Courville, A., Bengio, Y., Ghahramani, Z., Welling, M.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 3, pp. 2672–2680 (2014)Google Scholar
- 2.Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks (2015). arXiv preprint: arXiv:1511.06434
- 3.Dong, H., Neekhara, P., Wu, C., Guo, Y.: Unsupervised image-to-image translation with generative adversarial networks (2017). arXiv preprint: arXiv:1701.02676
- 4.Perarnau, G., van de Weijer, J., Raducanu, B., Alvarez, J.M.: Invertible conditional gans for image editing (2016). arXiv preprint: arXiv:1611.06355
- 5.Creswell, A., Bharath, A.A.: Inverting the generator of a generative adversarial network (2016). arXiv preprint: arXiv:1611.05644
- 6.Donahue, J., Krahenbuhl, P., Darrell, T.: Adversarial feature learning (2016). arXiv preprint: arXiv:1605.09782
- 7.Dumoulin, V., Belghazi, I., Poole, B., Lamb, A., Arjovsky, M., Mastropietro, O., Courville, A.: Adversarially learned inference (2016). arXiv preprint: arXiv:1606.00704
- 8.Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3730–3738 (2015)Google Scholar
- 9.Niu, X.M., Jiao, Y.H.: An overview of perceptual hashing. Acta Electronica Sin. 36(7), 1405–1411 (2008)Google Scholar
- 11.Hinton, G.E.: Learning distributed representations of concepts. In: Proceedings of the Eighth Annual Conference of the Cognitive Science Society, Amherst, MA, vol. 1, p. 12 (1986)Google Scholar
- 12.Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks (2016). arXiv preprint: arXiv:1611.07004