CoCoG：基于人类概念表示的可控视觉刺激生成
CoCoG: Controllable Visual Stimuli Generation based on Human Concept Representations
AI总结：
提出CoCoG框架，通过提取可解释概念预测人类决策并生成可控视觉刺激，在THINGS-similarity数据集上以64.07%准确率预测人类行为，并能通过干预概念操纵相似性判断。
摘要：
认知科学的一个核心问题是理解人类如何处理视觉对象，即从高维视觉刺激中揭示人类的低维概念表示空间。生成具有可控概念的视觉刺激是关键。然而，目前人工智能领域尚无生成模型能够解决这一问题。在此，我们提出了基于概念的可控生成（CoCoG）框架。CoCoG由两个组件构成：一个简单而高效的AI智能体，用于提取可解释概念并预测视觉相似性判断任务中的人类决策；以及一个条件生成模型，用于在给定概念时生成视觉刺激。我们从人类行为预测准确率和可控生成能力两个方面量化了CoCoG的性能。基于CoCoG的实验表明：1）CoCoG中可靠的概念嵌入能够在THINGS-similarity数据集中以64.07%的准确率预测人类行为；2）CoCoG能够通过概念控制生成多样化的对象；3）CoCoG能够通过干预关键概念来操纵人类相似性判断行为。CoCoG提供具有可控概念的视觉对象，以推进我们对人类认知中因果关系的理解。CoCoG的代码可在https://github.com/ncclab-sustech/CoCoG获取。
英文摘要：
A central question for cognitive science is to understand how humans process visual objects, i.e, to uncover human low-dimensional concept representation space from high-dimensional visual stimuli. Generating visual stimuli with controlling concepts is the key. However, there are currently no generative models in AI to solve this problem. Here, we present the Concept based Controllable Generation (CoCoG) framework. CoCoG consists of two components, a simple yet efficient AI agent for extracting interpretable concept and predicting human decision-making in visual similarity judgment tasks, and a conditional generation model for generating visual stimuli given the concepts. We quantify the performance of CoCoG from two aspects, the human behavior prediction accuracy and the controllable generation ability. The experiments with CoCoG indicate that 1) the reliable concept embeddings in CoCoG allows to predict human behavior with 64.07\% accuracy in the THINGS-similarity dataset; 2) CoCoG can generate diverse objects through the control of concepts; 3) CoCoG can manipulate human similarity judgment behavior by intervening key concepts. CoCoG offers visual objects with controlling concepts to advance our understanding of causality in human cognition. The code of CoCoG is available at \url{https://github.com/ncclab-sustech/CoCoG}.
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。
