Reconstructing faces from fMRI patterns using deep generative neural networks
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Although distinct categories are reliably decoded from fMRI brain responses, it has proved more difficult to distinguish visually similar inputs, such as different faces. Here, we apply a recently developed deep learning system to reconstruct face images from human fMRI. We trained a variational auto-encoder (VAE) neural network using a GAN (Generative Adversarial Network) unsupervised procedure over a large data set of celebrity faces. The auto-encoder latent space provides a meaningful, topologically organized 1024-dimensional description of each image. We then presented several thousand faces to human subjects, and learned a simple linear mapping between the multi-voxel fMRI activation patterns and the 1024 latent dimensions. Finally, we applied this mapping to novel test images, translating fMRI patterns into VAE latent codes, and codes into face reconstructions. The system not only performed robust pairwise decoding (>95% correct), but also accurate gender classification, and even decoded which face was imagined, rather than seen.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
The fusiform face area: a module in human extrastriate cortex specialized for face perception
Kanwisher, N., McDermott, J., & Chun, M. M. (1997) · The Journal of Neuroscience · doi:10.1523/jneurosci.17-11-04302.1997 · Cited by 7,738 · cited 1×
“This performance could reflect the strong involvement of temporal brain regions in high-level face processing 26-28 , as well as the primarily top-down nature of mental imagery 29 .”
BackgroundA multi-modal parcellation of human cerebral cortex
Glasser, M. F., Coalson, T. S., Robinson, E. C., Hacker, C. D., Harwell, J., Yacoub, E., Ugurbil, K., Andersson, J., Beckmann, C. F., Jenkinson, M., et al. (2016) · Nature · doi:10.1038/nature18933 · Cited by 5,111
Generative Adversarial Networks
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1406.2661 · Cited by 4,477
Distributed and overlapping representations of faces and objects in ventral temporal cortex
Haxby, J. V., Gobbini, M. I., Furey, M. L., Ishai, A., Schouten, J. L., & Pietrini, P. (2001) · Science · doi:10.1126/science.1063736 · Cited by 3,940 · cited 5×
“Across all voxel selections, PCA always produced lower accuracies than VAE–GAN—though this difference did not reach statistical significance given our limited subject number (across all three voxel selections, χ2(1) ≥ 3, p > 0.”
BackgroundInfluentialCircular analysis in systems neuroscience: the dangers of double dipping
Kriegeskorte, N., Simmons, W. K., Bellgowan, P. S. F., & Baker, C. I. (2009) · Nature Neuroscience · doi:10.1038/nn.2303 · Cited by 2,696
Kosslyn, S. M., Ganis, G., & Thompson, W. L. (2001) · Nature Reviews Neuroscience · doi:10.1038/35090055 · Cited by 1,894 · cited 1×
“…properties, implicitly reflected in their objective functions: they must somehow “unfold” the complexity of the representation space for face images (in other words, flatten the “face manifold” 15 ), making it linear or as close to linear as possible, so that it can be easily manipulated.”
BackgroundDecoding the visual and subjective contents of the human brain
Kamitani, Y., & Tong, F. (2005) · Nature Neuroscience · doi:10.1038/nn1444 · Cited by 1,829
Using goal-driven deep learning models to understand sensory cortex
Yamins, D. L. K., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4244 · Cited by 1,621
The Code for Facial Identity in the Primate Brain
Chang, L., & Tsao, D. Y. (2017) · Cell · doi:10.1016/j.cell.2017.05.011 · Cited by 644
Cited by
Higgins, I., Chang, L., Langston, V., Hassabis, D., Summerfield, C., Tsao, D., & Botvinick, M. (2021) · Nature Communications · doi:10.1038/s41467-021-26751-5 · Cited by 162
Deep learning and the global workspace theory
VanRullen, R., & Kanai, R. (2021) · Trends in Neurosciences · doi:10.1016/j.tins.2021.04.005 · Cited by 128
Generative AI for brain image computing and brain network computing: a review
Gong, C., Jing, C., Chen, X., Pun, C. M., Huang, G., Saha, A., Nieuwoudt, M., Li, H.-X., Hu, Y., & Wang, S. (2023) · Frontiers in Neuroscience · doi:10.3389/fnins.2023.1203104 · Cited by 111
A systematic collection of medical image datasets for deep learning
Li, J., Zhu, G., Hua, C., Feng, M., BasheerBennamoun, Li, P., Lu, X., Song, J., Shen, P., Xu, X., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.12864 · Cited by 61
Spagna, A., Hajhajate, D., Liu, J., & Bartolomeo, P. (2021) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2020.12.029 · Cited by 33
Metadata
- Authors
- VanRullen, R., & Reddy, L.
- Venue
- Communications Biology
- Published
- 2019-05-21
- Volume
- 2
- Issue
- 1
- Pages
- 193-193
- ISSN
- 2399-3642 (ISSN-L)
- OpenAlex
- W2897938635
- Cited by
- 155
- References
- 14
- FWCI
- 8.79
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Reconstructing faces from fMRI patterns using deep generative neural networks. https://app.cochat.ai/papers/10.1038/s42003-019-0438-y
- The paper
- VanRullen, R., & Reddy, L. (2019). Reconstructing faces from fMRI patterns using deep generative neural networks. Communications Biology. https://doi.org/10.1038/s42003-019-0438-y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.