Brain-Supervised Image Editing

Despite recent advances in deep neural models for semantic image editing, present approaches are dependent on explicit human input. Previous work assumes the availability of manually curated datasets for supervised learning, while for unsupervised approaches the human inspection of discovered components is required to identify those which modify worthwhile semantic features. Here, we present a novel alternative: the utilization of brain responses as a supervision signal for learning semantic feature representations. Participants (N=30) in a neurophysiological experiment were shown artificially generatedfaces and instructed to look for a particular semantic feature, such as old or smiling, while their brain responses were recorded via electroencephalography (EEG). Using supervision signals inferredfrom these responses, semantic features within the latent space of a generative adversarial network (GAN) were learned and then used to edit semantic features of new images. We show that implicit brain supervision achieves comparable semantic image editing performance to explicit manual labeling. This work demonstrates the feasibility of utilizing implicit human reactions recorded via brain-computer interfaces for semantic image editing and interpretation.

Automated summary

This study proposes a novel approach that utilizes brain responses as a supervision signal for learning semantic feature representations. By recording participants' brain responses while they view facial images, researchers are able to learn the latent space of a generative adversarial network (GAN) that can be used to edit semantic features of new images. The experiments demonstrate that implicit brain supervision achieves a comparable semantic image editing performance to explicit manual labeling.