Self-Supervised Natural Image Reconstruction and Large-Scale Semantic Classification from Brain Activity
Preprint
Abstract
Reconstructing natural images and decoding their semantic category from fMRI brain recordings is challenging. Acquiring sufficient pairs of images and their corresponding fMRI responses, which span the huge space of natural images, is prohibitive. We present a novel self-supervised approach that goes well beyond the scarce paired data, for achieving both: (i) state-of-the art fMRI-to-image reconstruction, and (ii) first-ever large-scale semantic classification from fMRI responses. By imposing cycle consistency between a pair of deep neural networks (from image-to-fMRI & from fMRI-to-image), we train our image reconstruction network on a large number of “unpaired” natural images (images without fMRI recordings) from many novel semantic categories. This enables to adapt our reconstruction network to a very rich semantic coverage without requiring any explicit semantic supervision. Specifically, we find that combining our self-supervised training with high-level perceptual losses , gives rise to new reconstruction & classification capabilities. In particular, this perceptual training enables to classify well fMRIs of never-before-seen semantic classes, without requiring any class labels during training . This gives rise to: (i) Unprecedented image-reconstruction from fMRI of never-before-seen images (evaluated by image metrics and human testing), and (ii) Large-scale semantic classification of categories that were never-before-seen during network training. Such large-scale (1000-way) semantic classification from fMRI recordings has never been demonstrated before . Finally, we provide evidence for the biological consistency of our learned model.Keywords
All Related Versions
- Published version: NeuroImage, 254, 119121.
This publication has 53 references indexed in Scilit:
- Computational neuroimaging and population receptive fieldsTrends in Cognitive Sciences, 2015
- Tripartite Organization of the Ventral Stream by Animacy and Object SizeThe Journal of Neuroscience, 2013
- Reconstructing Visual Experiences from Brain Activity Evoked by Natural MoviesCurrent Biology, 2011
- Bayesian Reconstruction of Natural Images from Human Brain ActivityNeuron, 2009
- Whither the hypercolumn?The Journal of Physiology, 2009
- Identifying natural images from human brain activityNature, 2008
- Distributed and Overlapping Representations of Faces and Objects in Ventral Temporal CortexScience, 2001
- Borders of Multiple Visual Areas in Humans Revealed by Functional Magnetic Resonance ImagingScience, 1995
- Iso-orientation domains in cat visual cortex are arranged in pinwheel-like patternsNature, 1991
- Role of Serotonergic Input in the Regulation of the β-Adrenergic Receptor-Coupled Adenylate Cyclase SystemScience, 1982