Research map / Probabilistic and scientific modeling / Dynamical systems
Reconstructing perceived faces from brain activations with deep adversarial neural decoding
Yağmur Güçlütürk, Umut Güçlü, Katja Seeliger, Sander Bosch, Rob van Lier, Marcel A. J. van Gerven
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 |
|---|---|---|---|
| replace eigenface (PCA) feature model with adversarially trained VGG-Face based DAND | brain decoding of faces · fMRI test S1 | feature similarity: 0.1475 -> 0.1900 | Improved |
| replace eigenface feature model with DAND | brain decoding of faces · fMRI test S2 | Pearson correlation: 0.2241 -> 0.4722 | Improved |
| replace identity transform with DAND | brain decoding of faces · fMRI test S1 | structural similarity: 0.3744 -> 0.4662 | Improved |
| replace identity transform with DAND | brain decoding of faces · fMRI test S2 | feature similarity: 0.1254 -> 0.1867 | Improved |
| use VGG-ImageNet instead of VGG-Face as latent feature model (ablation) | DAND · fMRI face reconstruction | reconstruction performance | Hurt |
| eigenface latent features instead of DAND for upper bound (LF) | reconstruction from latent features · fMRI test | Pearson correlation: 0.9875 -> 0.7181 | Mixed |
| compare reconstruction from brain vs random latent features | DAND · fMRI test | feature similarity ratio: 0.5181 -> 0.6546 | Improved |
| stimulus complexity as factor | DAND reconstruction accuracy · fMRI test 48 faces | correlation with accuracy: r = -0.3067 | Hurt |
| masculinity of face | DAND reconstruction accuracy · fMRI test 48 faces | correlation with accuracy: r = 0.3841 | Improved |
| femininity of face | DAND reconstruction accuracy · fMRI test 48 faces | correlation with accuracy: r = -0.3961 | Hurt |
| attractiveness, ethnicity, prototypicality of face | DAND reconstruction accuracy · fMRI test 48 faces | reconstruction accuracy | No clear effect |
| identify reconstruction among group sharing similar features vs not | DAND identification · fMRI test | identification accuracy | No clear effect |
Closest papers by meaning
- See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI (AAAI 2025 · similarity 0.86)
- $i$MIND: Insightful Multi-subject Invariant Neural Decoding (NeurIPS 2025 · similarity 0.85)
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.84)
- MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity (NeurIPS 2024 · similarity 0.84)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.84)
- ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding (NeurIPS 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.
