NCCVHCJul 20, 2024

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

arXiv:2407.14949v14 citationsh-index: 6Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for better controllable image generation methods for researchers studying human concept representation, though it appears incremental as it builds on prior work with a training-free guidance algorithm.

The study tackled the problem of underdeveloped methods for controllable image generation in concept space by introducing CoCoG-2, a framework that integrates generated visual stimuli into similarity judgment tasks to explore human concept representation, resulting in a versatile tool for creating experimental stimuli and validating hypotheses.

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}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes