AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

Jingyuan Sun, Mingxiao Li, Zijiao Chen, Yunhao Zhang, Shaonan Wang, Marie-Francine Moens

NeurIPS 2023 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 10 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the proposed FRL + LDM instead of DC-LDMVisual reconstruction · GOD subject 350-way-top-1 accuracy: 17.999 -> 25.080Improved
Jointly optimize fMRI and image reconstruction losses rather than setting either loss weight to zero (ablation)FRL Phase 2 · GOD subject 350-way-top-1 accuracyImproved
Set the fMRI reconstruction loss weight to 0.25 and the image reconstruction loss weight to 1.5 (ablation)FRL Phase 2 · GOD subject 350-way-top-1 accuracyImproved
Use a higher fMRI mask ratio and a lower image mask ratio (ablation)FRL Phase 2 · GOD subject 350-way-top-1 accuracyImproved
Set the fMRI mask ratio to 0.75 and the image mask ratio to 0.5 (ablation)FRL Phase 2 · GOD subject 350-way-top-1 accuracyImproved
Use a decoder depth of 6 layers (ablation)FRL Phase 2 auto-encoders · GOD subject 350-way-top-1 accuracyImproved
Use a decoder that is too shallow or too deep instead of a depth of 6 layers (ablation)FRL Phase 2 auto-encoders · GOD subject 350-way-top-1 accuracyHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy