Controlling generative models with continuous factors of variations
Recent deep generative models are able to provide photo-realistic images as well as visual or textual content embeddings useful to address various tasks of computer vision and natural language processing. Their usefulness is nevertheless often limited by the lack of control over the generative process or the poor understanding of the learned representation. To overcome these major issues, very recent work has shown the interest of studying the semantics of the latent space of generative models. In this paper, we propose to advance on the interpretability of the latent space of generative models by introducing a new method to find meaningful directions in the latent space of any generative model along which we can move to control precisely specific properties of the generated image like the position or scale of the object in the image. Our method does not require human annotations and is particularly well suited for the search of directions encoding simple transformations of the generated image, such as translation, zoom or color variations. We demonstrate the effectiveness of our method qualitatively and quantitatively, both for GANs and variational auto-encoders.
Code (1)
Tasks
TranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Discond-VAE: Disentangling Continuous Factors from the Discrete
In the real-world data, there are common variations shared by all classes (e.g. category label) and exclusive variations of each class. We propose a variant of VAE capable of disentangling both of these variations. To re…
DisentanglementLearning Disentangled Joint Continuous and Discrete Representations
We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders w…
Self-Learning Transformations for Improving Gaze and Head Redirection
Many computer vision tasks rely on labeled data. Rapid progress in generative modeling has led to the ability to synthesize photorealistic images. However, controlling specific aspects of the generation process such that…
DisentanglementGaze EstimationSelf-LearningLearning and controlling the source-filter representation of speech with a variational autoencoder
Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from…
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View
From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate …
Contrastive LearningDisentanglementRepresentation Learning