Related papers: Toward a Visual Concept Vocabulary for GAN Latent Space

Toward a Visual Concept Vocabulary for GAN Latent Space

URL: http://arxiv.org/abs/2110.04292v1
Date: Fri, 8 Oct 2021 17:58:19 GMT
Title: Toward a Visual Concept Vocabulary for GAN Latent Space
Authors: Sarah Schwettmann, Evan Hernandez, David Bau, Samuel Klein, Jacob Andreas, Antonio Torralba
Abstract summary: This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built from three components: automatic identification of perceptually salient directions based on their layer selectivity; human annotation of these directions with free-form, compositional natural language descriptions. Experiments show that concepts learned with our approach are reliable and composable -- generalizing across classes, contexts, and observers.
Score: 74.12447538049537
License: http://creativecommons.org/licenses/by-sa/4.0/
Abstract: A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these transformations rely on either a fixed vocabulary of pre-specified visual concepts, or on unsupervised disentanglement techniques whose alignment with human judgments about perceptual salience is unknown. This paper introduces a new method for building open-ended vocabularies of primitive visual concepts represented in a GAN's latent space. Our approach is built from three components: (1) automatic identification of perceptually salient directions based on their layer selectivity; (2) human annotation of these directions with free-form, compositional natural language descriptions; and (3) decomposition of these annotations into a visual concept vocabulary, consisting of distilled directions labeled with single words. Experiments show that concepts learned with our approach are reliable and composable -- generalizing across classes, contexts, and observers, and enabling fine-grained manipulation of image style and content.