Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets
This addresses the difficulty of training inverse models for GANs, which is important for applications like image searching and translation, but it appears incremental as it builds on existing autoencoder and GAN frameworks.
The paper tackles the challenging problem of learning the inverse mapping of GAN generators, proposing an autoencoder-based method that minimizes differences between input and output images to improve training and performance. Experimental results show it outperforms traditional approaches in image searching tasks.
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.