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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use the proposed FRL + LDM instead of DC-LDM | Visual reconstruction · GOD subject 3 | 50-way-top-1 accuracy: 17.999 -> 25.080 | Improved |
| Jointly optimize fMRI and image reconstruction losses rather than setting either loss weight to zero (ablation) | FRL Phase 2 · GOD subject 3 | 50-way-top-1 accuracy | Improved |
| Set the fMRI reconstruction loss weight to 0.25 and the image reconstruction loss weight to 1.5 (ablation) | FRL Phase 2 · GOD subject 3 | 50-way-top-1 accuracy | Improved |
| Use a higher fMRI mask ratio and a lower image mask ratio (ablation) | FRL Phase 2 · GOD subject 3 | 50-way-top-1 accuracy | Improved |
| Set the fMRI mask ratio to 0.75 and the image mask ratio to 0.5 (ablation) | FRL Phase 2 · GOD subject 3 | 50-way-top-1 accuracy | Improved |
| Use a decoder depth of 6 layers (ablation) | FRL Phase 2 auto-encoders · GOD subject 3 | 50-way-top-1 accuracy | Improved |
| 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 3 | 50-way-top-1 accuracy | Hurt |
Closest papers by meaning
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.89)
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.89)
- Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex (NeurIPS 2025 · similarity 0.88)
- MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding (NeurIPS 2025 · similarity 0.88)
- In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain (NeurIPS 2025 · similarity 0.88)
- Neuro-Vision to Language: Enhancing Brain Recording-based Visual Reconstruction and Language Interaction (NeurIPS 2024 · similarity 0.87)
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.
