Research map / Optimization / Optimizers
Deep Hyperalignment
Muhammad Yousefnezhad, Daoqiang Zhang
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 |
|---|---|---|---|
| Use DHA instead of CAE | post-alignment classification · DS005 | accuracy (%): 94.25±0.76 -> 97.92±0.82 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS105 | accuracy (%): 54.52±0.80 -> 60.39±0.68 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS107 | accuracy (%): 72.16±0.43 -> 73.05±0.63 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS116 | accuracy (%): 91.49±0.67 -> 90.28±0.71 | Hurt |
| Use DHA instead of CAE | post-alignment classification · DS117 | accuracy (%): 95.92±0.67 -> 97.99±0.94 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS005 | AUC (%): 91.24±0.61 -> 96.91±0.82 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS105 | AUC (%): 52.16±0.63 -> 59.57±0.32 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS107 | AUC (%): 72.33±0.79 -> 70.23±0.92 | Hurt |
| Use DHA instead of CAE | post-alignment classification · DS116 | AUC (%): 87.53±0.72 -> 89.93±0.24 | Improved |
| Use DHA instead of CAE | post-alignment classification · DS117 | AUC (%): 91.49±0.33 -> 96.13±0.32 | Improved |
| Enable feature selection (use fewer than all features) (ablation) | DHA · DS105 and DS107 | classification performance | Improved |
Closest papers by meaning
- MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data (ICML 2025 · similarity 0.82)
- Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding (AAAI 2025 · similarity 0.81)
- DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases (NeurIPS 2025 · similarity 0.80)
- MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction (AAAI 2025 · similarity 0.80)
- Sparse components distinguish visual pathways & their alignment to neural networks (ICLR 2025 · similarity 0.80)
- MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data (ICML 2024 · similarity 0.80)
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.
