Representation Decomposition for Image Manipulation and Beyond
This enables manipulation of trained generative models without retraining, addressing a bottleneck in representation disentanglement for image editing applications.
The paper tackles the problem of decomposing latent representations in existing generative models into content and attribute features for image manipulation, proposing dec-GAN which achieves this decomposition with effectiveness and robustness confirmed on multiple datasets.
Representation disentanglement aims at learning interpretable features, so that the output can be recovered or manipulated accordingly. While existing works like infoGAN and AC-GAN exist, they choose to derive disjoint attribute code for feature disentanglement, which is not applicable for existing/trained generative models. In this paper, we propose a decomposition-GAN (dec-GAN), which is able to achieve the decomposition of an existing latent representation into content and attribute features. Guided by the classifier pre-trained on the attributes of interest, our dec-GAN decomposes the attributes of interest from the latent representation, while data recovery and feature consistency objectives enforce the learning of our proposed method. Our experiments on multiple image datasets confirm the effectiveness and robustness of our dec-GAN over recent representation disentanglement models.