Concept Lens: Visually Analyzing the Consistency of Semantic Manipulation in GANs

TL;DR

Concept Lens is a visualization tool that helps users explore and understand the semantic manipulation capabilities of GANs by revealing concept relationships and consistency in image editing.

Contribution

We introduce Concept Lens, a novel visualization design for analyzing concept diversity, relationships, and control in GANs' latent spaces.

Findings

Reveals consistent semantic manipulations in GAN-generated images

Helps diagnose limitations in concept discovery methods

Supports hierarchical exploration of concepts and images

Abstract

As applications of generative AI become mainstream, it is important to understand what generative models are capable of producing, and the extent to which one can predictably control their outputs. In this paper, we propose a visualization design, named Concept Lens, for jointly navigating the data distribution of a generative model, and concept manipulations supported by the model. Our work is focused on modern vision-based generative adversarial networks (GAN), and their learned latent spaces, wherein concept discovery has gained significant interest as a means of image manipulation. Concept Lens is designed to support users in understanding the diversity of a provided set of concepts, the relationship between concepts, and the suitability of concepts to give semantic controls for image generation. Key to our approach is the hierarchical grouping of concepts, generated images, and the associated joint exploration. We show how Concept Lens can reveal consistent semantic manipulations for editing images, while also serving as a diagnostic tool for studying the limitations and trade-offs of concept discovery methods.