Research map / Image generation / Autoregressive and latent generation
D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment
Chenglong Yu, Shuai Shen, Xiangsheng Li, Yang Li
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 Mamba with frequency-oriented FOMamba in the EEG encoder (ablation) | FSTDE without DDLG · THINGS-EEG 200-way | top-1 accuracy (%): 27.75 -> 31.18 | Improved |
| replace Transformer with FOMamba (ablation) | FSTDE without DDLG · THINGS-EEG 200-way | top-1 accuracy (%): 25.30 -> 31.18 | Improved |
| add full bidirectional DDLG (ablation) | FOMamba encoder · THINGS-EEG 200-way | top-1 accuracy (%): 31.18 -> 37.96 | Improved |
| add full DDLG (ablation) | Mamba encoder · THINGS-EEG 200-way | top-1 accuracy (%): 27.75 -> 30.10 | Improved |
| add full DDLG (ablation) | Transformer encoder · THINGS-EEG 200-way | top-1 accuracy (%): 25.30 -> 27.30 | Improved |
| use bidirectional DDLG instead of only EEG-to-image diffusion (ablation) | FOMamba encoder · THINGS-EEG 200-way | top-1 accuracy (%): 35.36 -> 37.96 | Improved |
| add DDLG (ablation) | FOMamba encoder · THINGS-EEG 50-way | top-5 accuracy (%): 84.58 -> 87.09 | Improved |
| bound damping rho_max at 0.995 instead of 1.0 (ablation) | FOMamba · THINGS-EEG 200-way | top-1 accuracy (%) | Improved |
| set rho_min around 0.5-0.7 rather than lower or higher (ablation) | FOMamba · THINGS-EEG 200-way | top-1 accuracy (%) | Improved |
| D2-FOSA versus MB2C on EEGCVPR40 (5-95 Hz) top-5 | D2-FOSA · EEGCVPR40 (5-95 Hz filter) | top-5 accuracy (%): 99.18 -> 98.75 | Hurt |
| D2-FOSA versus VE-SDN on THINGS-EEG intra-subject | D2-FOSA · THINGS-EEG 200-way (intra-subject, avg) | top-1 accuracy (%): 37.2 -> 38.0 | Improved |
Closest papers by meaning
- What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment (NeurIPS 2026 · similarity 0.90)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.90)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.89)
- EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals (NeurIPS 2024 · similarity 0.89)
- Neural‑Visual Decoding via Cognitive‑guided Adaptive Blurring and Information‑Constrained Alignment (NeurIPS 2026 · similarity 0.87)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · 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.
