Information Compensation for Deep Conditional Generative Networks
This addresses a key limitation in generative modeling for AI/ML applications, though it appears incremental as it builds on existing GAN frameworks.
The paper tackles the problem of poor disentanglement of latent factors in unsupervised conditional GANs by proposing an Information Compensation Connection to mitigate information loss during deconvolution, and it reports better disentanglement compared to state-of-the-art methods.
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data. However, one of their weaknesses lies in their poor ability to separate, or disentangle, the different factors that characterize the representation encoded in their latent space. To address this issue, we propose a novel structure for unsupervised conditional GANs powered by a novel Information Compensation Connection (IC-Connection). The proposed IC-Connection enables GANs to compensate for information loss incurred during deconvolution operations. In addition, to quantify the degree of disentanglement on both discrete and continuous latent variables, we design a novel evaluation procedure. Our empirical results suggest that our method achieves better disentanglement compared to the state-of-the-art GANs in a conditional generation setting.