arrow
返回

Brain-Supervised Conditional Generative Modeling

delete2025-03-01
delete0
delete
OA
AI
J
Jun Ma
T
Tuukka Ruotsalo *
DOI:10.1109/THMS.2025.3537339delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Present machine learning approaches to steer generative models rely on the availability of manual human input. We propose an alternative approach to supervising generative machine learning models by directly detecting task-relevant information from brain responses. That is, requiring humans only to perceive stimulus and react to it naturally. Brain responses of participants (N=30) were recorded via electroencephalography (EEG) while they perceived artificially generated images of faces and were instructed to look for a particular semantic feature, such as smile or young. A supervised adversarial autoencoder was trained to disentangle semantic image features by using EEG data as a supervision signal. The model was subsequently conditioned to generate images matching users' intentions without additional human input. The approach was evaluated in a validation study comparing brain-conditioned models to manually conditioned and randomly conditioned alternatives. Human assessors scored the saliency of images generated from different models according to the target visual features (e.g., which face image is more smiling or more young). The results show that brain-supervised models perform comparably to models trained with manually curated labels, without requiring any manual input from humans.
Keyword:
Brain modeling
Electroencephalography
Semantics
Visualization
Functional magnetic resonance imaging
Faces
Brain
Manuals
Image reconstruction
Training data
Electroencephalography (EEG)
generative modeling
neuroimaging

期刊

IEEE Transactions on Human-Machine Systems 封面图
IEEE Transactions on Human-Machine Systems
IF:
4.4
论文数:
1.1K
被引数:
4.4K

机构

U
university of helsinki
学者数:
2.3K
论文数: 827
被引数: 2.5W
引用论文

引用论文

暂无论文信息