Enregistré dans:
Détails bibliographiques
Auteurs principaux: Grizou, Jonathan, de la Torre-Ortiz, Carlos, Ruotsalo, Tuukka
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.11151
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909939274874880
author Grizou, Jonathan
de la Torre-Ortiz, Carlos
Ruotsalo, Tuukka
author_facet Grizou, Jonathan
de la Torre-Ortiz, Carlos
Ruotsalo, Tuukka
contents We consider the problem of recovering a mental target (e.g., an image of a face) that a participant has in mind from paired EEG (i.e., brain responses) and image (i.e., perceived faces) data collected during interactive sessions without access to labeled information. The problem has been previously explored with labeled data but not via self-calibration, where labeled data is unavailable. Here, we present the first framework and an algorithm, CURSOR, that learns to recover unknown mental targets without access to labeled data or pre-trained decoders. Our experiments on naturalistic images of faces demonstrate that CURSOR can (1) predict image similarity scores that correlate with human perceptual judgments without any label information, (2) use these scores to rank stimuli against an unknown mental target, and (3) generate new stimuli indistinguishable from the unknown mental target (validated via a user study, N=53).
format Preprint
id arxiv_https___arxiv_org_abs_2506_11151
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
Grizou, Jonathan
de la Torre-Ortiz, Carlos
Ruotsalo, Tuukka
Computer Vision and Pattern Recognition
Human-Computer Interaction
We consider the problem of recovering a mental target (e.g., an image of a face) that a participant has in mind from paired EEG (i.e., brain responses) and image (i.e., perceived faces) data collected during interactive sessions without access to labeled information. The problem has been previously explored with labeled data but not via self-calibration, where labeled data is unavailable. Here, we present the first framework and an algorithm, CURSOR, that learns to recover unknown mental targets without access to labeled data or pre-trained decoders. Our experiments on naturalistic images of faces demonstrate that CURSOR can (1) predict image similarity scores that correlate with human perceptual judgments without any label information, (2) use these scores to rank stimuli against an unknown mental target, and (3) generate new stimuli indistinguishable from the unknown mental target (validated via a user study, N=53).
title Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
url https://arxiv.org/abs/2506.11151