There are 2 submodules in our model — a contrastive submodule and a diffusion prior submodule, but they still form 1 model because they are trained end-to-end. In the final architecture that we picked there is a common backbone that maps from fMRIs to an intermediate space. Then there is an MLP projector that produces the retrieval embeddings and a diffusion prior that produces the stable diffusion embeddings.
Both the prior and MLP projector makes use of the same intermediate space, and the backbone + projector + prior are all trained end-to-end (the contrastive loss on the projector output and mse loss on prior outputs are simply added together).
We found that this works better than first training a contrastive model then freezing it and training a diffusion prior on its outputs (similar to CLIP + DALLE-2). That is, the retrieval objective improves reconstruction and the reconstruction objective slightly improves retrieval.
This is mostly correct, except that there is only one model. This model takes an fMRI and predicts 2 outputs. The first is specialized for retrieval and the second can be fed into a diffusion model to reconstruct images.
You can see the comparison in performance between LAION-5B retrieval and actual reconstructions in the paper. When retrieving from a large enough database like LAION-5B, we can get images that are quite similar to the seen images in terms of high level content, but not so similar in low-level details (relative position of objects, colors, texture, etc). Reconstruction with diffusion models does much better in terms of low-level metrics.
We did have a face reconstruction project planned. It is on the back-burner for now. That one will be based on something like the Celeb-A dataset instead of the Natural Scenes Dataset (images from MS-COCO) used here.
Both the prior and MLP projector makes use of the same intermediate space, and the backbone + projector + prior are all trained end-to-end (the contrastive loss on the projector output and mse loss on prior outputs are simply added together).
We found that this works better than first training a contrastive model then freezing it and training a diffusion prior on its outputs (similar to CLIP + DALLE-2). That is, the retrieval objective improves reconstruction and the reconstruction objective slightly improves retrieval.