CoCoG-2: Controllable generation of visual stimuli for understanding human concept representation

TL;DR

CoCoG-2 is a novel framework that enables controllable generation of visual stimuli based on human concepts, facilitating the study of concept representation and decision-making through similarity judgment tasks.

Contribution

It introduces a training-free guidance algorithm for flexible, controllable image generation in concept space, supporting experimental validation of human concept representations.

Findings

Versatile creation of stimuli for concept-based experiments

Supports various strategies for guiding visual stimuli generation

Demonstrates potential to validate hypotheses on concept-behavior relationships

Abstract

Humans interpret complex visual stimuli using abstract concepts that facilitate decision-making tasks such as food selection and risk avoidance. Similarity judgment tasks are effective for exploring these concepts. However, methods for controllable image generation in concept space are underdeveloped. In this study, we present a novel framework called CoCoG-2, which integrates generated visual stimuli into similarity judgment tasks. CoCoG-2 utilizes a training-free guidance algorithm to enhance generation flexibility. CoCoG-2 framework is versatile for creating experimental stimuli based on human concepts, supporting various strategies for guiding visual stimuli generation, and demonstrating how these stimuli can validate various experimental hypotheses. CoCoG-2 will advance our understanding of the causal relationship between concept representations and behaviors by generating visual stimuli. The code is available at \url{https://github.com/ncclab-sustech/CoCoG-2}.