🤖 AI Summary
This study addresses semantic-controllable editing of subjective first impressions of faces (e.g., trustworthiness, attractiveness). We propose the first end-to-end generative framework that models perceptual attribute changes as identity-preserving latent-space direction mappings, enabling unified, interpretable, attribute-directed editing across domains (real and synthetic). Our method integrates GAN latent-space manipulation, attribute-regression-guided directional optimization, and joint training on multi-source data, evaluated via dual assessment—human subjective ratings and model-based predictions. Experiments demonstrate high fidelity and strong identity preservation for edited images both within and across domains. Human evaluations confirm that perceptual shifts align with intended attributes and significantly outperform conventional statistical perturbation approaches. Furthermore, our analysis uncovers visual representation patterns underlying facial bias, offering insights into its perceptual foundations.
📝 Abstract
Humans tend to form quick subjective first impressions of non-physical attributes when seeing someone's face, such as perceived trustworthiness or attractiveness. To understand what variations in a face lead to different subjective impressions, this work uses generative models to find semantically meaningful edits to a face image that change perceived attributes. Unlike prior work that relied on statistical manipulation in feature space, our end-to-end framework considers trade-offs between preserving identity and changing perceptual attributes. It maps identity-preserving latent space directions to changes in attribute scores, enabling transformation of any input face along an attribute axis according to a target change. We train on real and synthetic faces, evaluate for in-domain and out-of-domain images using predictive models and human ratings, demonstrating the generalizability of our approach. Ultimately, such a framework can be used to understand and explain biases in subjective interpretation of faces that are not dependent on the identity.
