AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI

NeurIPS 2019 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 62 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Add training on external unlabeled images (ablation)Supervised fMRI-to-image reconstruction · fMRI on ImageNet2-way identification accuracy: 80.1% -> 83.2%Helped
Add self-supervised training on unlabeled test-fMRI (ablation)Supervised reconstruction with unlabeled-image training · fMRI on ImageNet2-way identification accuracy: 83.2% -> 85.3%Helped
Exclude the target test-fMRI from unlabeled fMRI training (ablation)Full method · fMRI on ImageNet2-way identification accuracy: 85.3% -> 84.1%Hurt
Add random shifts to input images during Encoder trainingImage-to-fMRI Encoder · fMRI-to-image reconstructionreconstruction qualityHelped

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