An EEG-based Image Annotation System
This addresses the problem of low annotation throughput for computer vision researchers, offering a novel approach that is not incremental but introduces a new paradigm.
The paper tackles the bottleneck of manual image annotation for deep learning by proposing an EEG-based system that uses brain signals to achieve an annotation rate of up to 10 images per second, with an F1-score of 0.88 on the test set.
The success of deep learning in computer vision has greatly increased the need for annotated image datasets. We propose an EEG (Electroencephalogram)-based image annotation system. While humans can recognize objects in 20-200 milliseconds, the need to manually label images results in a low annotation throughput. Our system employs brain signals captured via a consumer EEG device to achieve an annotation rate of up to 10 images per second. We exploit the P300 event-related potential (ERP) signature to identify target images during a rapid serial visual presentation (RSVP) task. We further perform unsupervised outlier removal to achieve an F1-score of 0.88 on the test set. The proposed system does not depend on category-specific EEG signatures enabling the annotation of any new image category without any model pre-training.