Optimizing the Latent Space of Generative Networks
Generative Adversarial Networks (GANs) have achieved remarkable results in the task of generating realistic natural images. In most successful applications, GAN models share two common aspects: solving a challenging saddle point optimization problem, interpreted as an adversarial game between a generator and a discriminator functions; and parameterizing the generator and the discriminator as deep convolutional neural networks. The goal of this paper is to disentangle the contribution of these two factors to the success of GANs. In particular, we introduce Generative Latent Optimization (GLO), a framework to train deep convolutional generators using simple reconstruction losses. Throughout a variety of experiments, we show that GLO enjoys many of the desirable properties of GANs: synthesizing visually-appealing samples, interpolating meaningfully between samples, and performing linear arithmetic with noise vectors; all of this without the adversarial optimization scheme.
Code (6)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
Many important problems in science and engineering, such as drug design, involve optimizing an expensive black-box objective function over a complex, high-dimensional, and structured input space. Although machine learnin…
Drug DesignMolecular Graph GenerationGenerative Co-Design of Antibody Sequences and Structures via Black-Box Guidance in a Shared Latent Space
Advancements in deep generative models have enabled the joint modeling of antibody sequence and structure, given the antigen-antibody complex as context. However, existing approaches for optimizing complementarity-determ…
Multi-Objective Latent Space Optimization of Generative Molecular Design Models
Molecular design based on generative models, such as variational autoencoders (VAEs), has become increasingly popular in recent years due to its efficiency for exploring high-dimensional molecular space to identify molec…
Optimizing Latent Space Directions For GAN-based Local Image Editing
Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introduci…
DisentanglementGenerative Adversarial NetworkCombining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
We consider the problem of optimizing combinatorial spaces (e.g., sequences, trees, and graphs) using expensive black-box function evaluations. For example, optimizing molecules for drug design using physical lab experim…
Bayesian OptimizationDrug DesignInductive Bias