Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability

Chen Wei, Chi Zhang, Jiachen Zou, Haotian Deng, Dietmar Heinke, Quanying Liu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:66322-66357, 2025.

Abstract

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 propose a systematic Boundary Alignment Manipulation (BAM) framework for studying human perceptual variability through image generation. BAM combines perceptual boundary sampling in ANNs and human behavioral experiments to systematically investigate this phenomenon. Our perceptual boundary sampling algorithm generates stimuli along ANN perceptual 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. Code and data for this work are publicly available.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wei25p, title = {Synthesizing Images on Perceptual Boundaries of {ANN}s for Uncovering and Manipulating Human Perceptual Variability}, author = {Wei, Chen and Zhang, Chi and Zou, Jiachen and Deng, Haotian and Heinke, Dietmar and Liu, Quanying}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {66322--66357}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wei25p/wei25p.pdf}, url = {https://proceedings.mlr.press/v267/wei25p.html}, abstract = {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 propose a systematic Boundary Alignment Manipulation (BAM) framework for studying human perceptual variability through image generation. BAM combines perceptual boundary sampling in ANNs and human behavioral experiments to systematically investigate this phenomenon. Our perceptual boundary sampling algorithm generates stimuli along ANN perceptual 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. Code and data for this work are publicly available.} }
Endnote
%0 Conference Paper %T Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability %A Chen Wei %A Chi Zhang %A Jiachen Zou %A Haotian Deng %A Dietmar Heinke %A Quanying Liu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wei25p %I PMLR %P 66322--66357 %U https://proceedings.mlr.press/v267/wei25p.html %V 267 %X 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 propose a systematic Boundary Alignment Manipulation (BAM) framework for studying human perceptual variability through image generation. BAM combines perceptual boundary sampling in ANNs and human behavioral experiments to systematically investigate this phenomenon. Our perceptual boundary sampling algorithm generates stimuli along ANN perceptual 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. Code and data for this work are publicly available.
APA
Wei, C., Zhang, C., Zou, J., Deng, H., Heinke, D. & Liu, Q.. (2025). Synthesizing Images on Perceptual Boundaries of ANNs for Uncovering and Manipulating Human Perceptual Variability. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:66322-66357 Available from https://proceedings.mlr.press/v267/wei25p.html.

Related Material