TY - GEN

T1 - Brain-Supervised Image Editing

AU - Davis, Keith M.

AU - De La Torre-Ortiz, Carlos

AU - Ruotsalo, Tuukka

N1 - Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - 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 generated faces 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 inferred from 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.

AB - 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 generated faces 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 inferred from 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.

KW - Image and video synthesis and generation

KW - Vision + X

UR - http://www.scopus.com/inward/record.url?scp=85141304372&partnerID=8YFLogxK

U2 - 10.1109/CVPR52688.2022.01793

DO - 10.1109/CVPR52688.2022.01793

M3 - Article in proceedings

AN - SCOPUS:85141304372

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 18459

EP - 18468

BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

PB - IEEE Computer Society Press

T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

Y2 - 19 June 2022 through 24 June 2022

ER -