用神经网络边界生成图像，揭示并操控人的感知差异
Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability
- 在神经网络决策边界生成刺激图像，诱发显著感知差异
- 246人参与11.7万次实验，构建包含1.9万张标注图像的variMNIST数据集
- 可预测并操控两人间感知分歧，适合个性化认知研究
人类在认知任务和日常生活中决策存在显著变异性，受任务难度、个体偏好与个人经验影响。理解这种跨个体的变异性对揭示人类在不确定与模糊情境下的感知与决策机制至关重要。我们提出计算框架BAM（边界对齐与操控框架），结合神经网络感知边界采样与人类行为实验，系统研究此现象。感知边界采样算法生成沿神经网络决策边界的数据，内在引发显著感知差异。该方法通过大规模行为实验验证，涉及246名参与者、116,715次试验，最终形成包含19,943张系统标注图像的variMNIST数据集。通过个性化模型对齐与对抗生成，建立了一种可靠方法，可同时预测并操控成对参与者的感知分歧。本工作弥合了计算模型与人类个体差异研究之间的鸿沟，为个性化感知分析提供了新工具。
原文摘要 · Abstract (English)
Human decision-making in cognitive tasks and daily life exhibits considerable variability, shaped by factors such as task difficulty, individual preferences, and personal experiences. Understanding this variability across individuals is essential for uncovering the perceptual and decision-making mechanisms that humans rely on when faced with uncertainty and ambiguity. We present a computational framework BAM (Boundary Alignment & Manipulation framework) that combines perceptual boundary sampling in ANNs and human behavioral experiments to systematically investigate this phenomenon. Our perceptual boundary sampling algorithm generates stimuli along ANN decision boundaries that intrinsically induce significant perceptual variability. The efficacy of these stimuli is empirically validated through large-scale behavioral experiments involving 246 participants across 116,715 trials, culminating in the variMNIST dataset containing 19,943 systematically annotated images. Through personalized model alignment and adversarial generation, we establish a reliable method for simultaneously predicting and manipulating the divergent perceptual decisions of pairs of participants. This work bridges the gap between computational models and human individual difference research, providing new tools for personalized perception analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。