概念透镜：可视化分析GAN中语义操控的一致性
Concept Lens: Visually Analyzing the Consistency of Semantic Manipulation in GANs
AI总结：
本文提出可视化工具Concept Lens，通过层次化分组和联合探索GAN潜在空间中的概念与生成图像，帮助分析语义操控一致性并诊断概念发现方法的局限。
摘要：
随着生成式人工智能的应用逐渐成为主流，理解生成模型能够产生什么内容，以及人们能在多大程度上可预测地控制其输出变得十分重要。本文提出了一种名为 Concept Lens 的可视化设计，用于联合导航生成模型的数据分布以及该模型所支持的概念操控。我们的工作聚焦于现代基于视觉的生成对抗网络（GAN）及其学习到的潜在空间，其中概念发现作为一种图像操控手段已引起广泛关注。Concept Lens 旨在支持用户理解给定概念集合的多样性、概念之间的关系，以及这些概念为图像生成提供语义控制的适用性。我们方法的关键在于对概念、生成图像进行层次化分组，并进行相关联的联合探索。我们展示了 Concept Lens 如何揭示用于编辑图像的一致语义操控，同时也可作为诊断工具，用于研究概念发现方法的局限性与权衡。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
