Table of Links
2 MindEye2 and 2.1 Shared-Subject Functional Alignment
2.2 Backbone, Diffusion Prior, & Submodules
2.3 Image Captioning and 2.4 Fine-tuning Stable Diffusion XL for unCLIP
3 Results and 3.1 fMRI-to-Image Reconstruction
3.3 Image/Brain Retrieval and 3.4 Brain Correlation
6 Acknowledgements and References
A Appendix
A.2 Additional Dataset Information
A.3 MindEye2 (not pretrained) vs. MindEye1
A.4 Reconstruction Evaluations Across Varying Amounts of Training Data
A.5 Single-Subject Evaluations
A.7 OpenCLIP BigG to CLIP L Conversion
A.9 Reconstruction Evaluations: Additional Information
A.10 Pretraining with Less Subjects
A.11 UMAP Dimensionality Reduction
A.13 Human Preference Experiments
A.11 UMAP Dimensionality Reduction
As discussed in Scotti et al. (2023), UMAP dimensionality reduction (McInnes et al., 2020) plots of disjointed CLIP fMRI embeddings next to aligned CLIP fMRI embeddings visualize how the diffusion prior effectively addresses the disjointed embedding spaces problem. Theoretically, multimodal contrastive learning will always produce disjointed embeddings because of the “modality gap” phenomenon whereby encoding modalities into a shared space restricts the effective embedding space to a narrow cone in geometric space (Liang et al., 2022).
This paper is available on arxiv under CC BY 4.0 DEED license.
Authors:
(1) Paul S. Scotti, Stability AI and Medical AI Research Center (MedARC);
(2) Mihir Tripathy, Medical AI Research Center (MedARC) and a Core contribution;
(3) Cesar Kadir Torrico Villanueva, Medical AI Research Center (MedARC) and a Core contribution;
(4) Reese Kneeland, University of Minnesota and a Core contribution;
(5) Tong Chen, The University of Sydney and Medical AI Research Center (MedARC);
(6) Ashutosh Narang, Medical AI Research Center (MedARC);
(7) Charan Santhirasegaran, Medical AI Research Center (MedARC);
(8) Jonathan Xu, University of Waterloo and Medical AI Research Center (MedARC);
(9) Thomas Naselaris, University of Minnesota;
(10) Kenneth A. Norman, Princeton Neuroscience Institute;
(11) Tanishq Mathew Abraham, Stability AI and Medical AI Research Center (MedARC).