Research map / Image generation / GANs
Conditional Generative Neural Decoding with Structured CNN Feature Prediction
Changde Du, Changying Du, Lijie Huang, Huiguang He
Read the paperCheck your idea against 137,217 papers
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 |
|---|---|---|---|
| add input, task and output structure modeling to multi-output regression (SMR vs independent SLR) | Voxel2Unit · Vim-1 | NMSE: .641 -> .549 | Improved |
| add input, task and output structure modeling (SMR vs SLR) | Voxel2Unit · FaceBold | NMSE: .724 -> .651 | Improved |
| add output structure to input+task structure (SMR-IT to SMR, sparse) (ablation) | SMR · Vim-1 | NMSE: .560 -> .549 | Improved |
| add input structure to output+task (SMR-OT to SMR, sparse) (ablation) | SMR · FaceBold | NMSE: .668 -> .651 | Improved |
| add sparsity (l1) on inverse covariance matrices (ablation) | SMR · Vim-1 | NMSE: .562 -> .549 | Improved |
| add sparsity (l1) on inverse covariance matrices (ablation) | SMR · FaceBold | NMSE: .660 -> .651 | Improved |
| use introspective conditional generation instead of CGAN | Unit2Pixel · Vim-1 | PCC: .493 -> .551 | Improved |
| use introspective conditional generation instead of CGAN | Unit2Pixel · FaceBold | SSIM: .831 -> .872 | Improved |
| use introspective conditional generation instead of CVAE | Unit2Pixel · Vim-1 | SSIM: .592 -> .675 | Improved |
| single structure only (SMR-T, I or O) vs SLR baseline (ablation) | SLR · Vim-1 | NMSE: .641 -> .578 | Improved |
Closest papers by meaning
- MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity (NeurIPS 2024 · similarity 0.86)
- ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding (NeurIPS 2025 · similarity 0.85)
- Multigranular Evaluation for Brain Visual Decoding (AAAI 2026 · similarity 0.85)
- MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs (NeurIPS 2025 · similarity 0.85)
- $i$MIND: Insightful Multi-subject Invariant Neural Decoding (NeurIPS 2025 · similarity 0.84)
- Toward Generalizing Visual Brain Decoding to Unseen Subjects (ICLR 2025 · similarity 0.84)
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.
