# Subject-Aware Multi-Granularity Alignment for Zero-Shot EEG-to-Image Retrieval

arXiv: https://arxiv.org/abs/2604.17782 · HTML: https://mlsanity.com/paper/2604.17782/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 30)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors](https://mlsanity.com/paper/2305.18274/) (2023)
- [Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding](https://mlsanity.com/paper/2211.06956/) (2022)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data](https://mlsanity.com/paper/2403.11207/) (2024)
- [Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway](https://mlsanity.com/paper/1411.6422/) (2014)
- [Decoding Natural Images from EEG for Object Recognition](https://mlsanity.com/paper/2308.13234/) (2023)
- [Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion](https://mlsanity.com/paper/2403.07721/) (2024)
- [Deep Learning Human Mind for Automated Visual Classification](https://mlsanity.com/paper/1609.00344/) (2016)
- [Brain decoding: toward real-time reconstruction of visual perception](https://mlsanity.com/paper/2310.19812/) (2023)
- [MindBridge: A Cross-Subject Brain Decoding Framework](https://mlsanity.com/paper/2404.07850/) (2024)
- [Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features](https://mlsanity.com/paper/2210.06756/) (2022)
- [DreamDiffusion: Generating High-Quality Images from Brain EEG Signals](https://mlsanity.com/paper/2306.16934/) (2023)
- [MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction](https://mlsanity.com/paper/2404.12630/) (2024)
- [Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior](https://mlsanity.com/paper/2503.04207/) (2025)
- [CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Information](https://mlsanity.com/paper/2412.10489/) (2024)
- [BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals](https://mlsanity.com/paper/2505.18185/) (2025)
- [Visual Neural Decoding via Improved Visual-EEG Semantic Consistency](https://mlsanity.com/paper/2408.06788/) (2024)
- [Object classification from randomized EEG trials](https://mlsanity.com/paper/2004.06046/) (2020)
- [MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data](https://mlsanity.com/paper/2502.05034/) (2025)
- [FoME: A Foundation Model for EEG using Adaptive Temporal-Lateral Attention Scaling](https://mlsanity.com/paper/2409.12454/) (2024)
- [Neural-MCRL: Neural Multimodal Contrastive Representation Learning for EEG-based Visual Decoding](https://mlsanity.com/paper/2412.17337/) (2024)
- [NeuroBridge: Bio-Inspired Self-Supervised EEG-to-Image Decoding via Cognitive Priors and Bidirectional Semantic Alignment](https://mlsanity.com/paper/2511.06836/) (2025)
- [NeuroCLIP: Brain-Inspired Prompt Tuning for EEG-to-Image Multimodal Contrastive Learning](https://mlsanity.com/paper/2511.09250/) (2025)
- [Deep Models, Shallow Alignment: Uncovering the Granularity Mismatch in Neural Decoding](https://mlsanity.com/paper/2601.21948/) (2026)
- [CrossPT-EEG: A Benchmark for Cross-Participant and Cross-Time Generalization of EEG-based Visual Decoding](https://mlsanity.com/paper/2406.07151/) (2024)
- [Decoding Visual Neural Representations by Multimodal with Dynamic Balancing](https://mlsanity.com/paper/2509.03433/) (2025)
- [Functional connectivity guided deep neural network for decoding high-level visual imagery](https://mlsanity.com/paper/2510.27075/) (2025)

## Built on by (most cited first, 4 of 4)

- [SCORE: Subject Coordinate Recovery for Label-Free Cross-Subject EEG-to-Image Retrieval](https://mlsanity.com/paper/2608.19134/) (2026)
- [CORTIVA: Candidate-Score Fusion of Complementary Visual Teachers for EEG- and MEG-to-Image Retrieval](https://mlsanity.com/paper/2608.01355/) (2026)
- [RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG](https://mlsanity.com/paper/2609.31698/) (2026)
- [Structured Visual Target Learning For Cross-Subject eeg-to-image retrieval](https://mlsanity.com/paper/2609.36971/) (2026)

## Abstract (arXiv)

Decoding visual content from electroencephalography (EEG) is important for understanding neural visual representations and developing non-invasive brain-computer interfaces. Existing approaches mainly improve EEG representation learning and cross-modal alignment while treating pretrained visual representations as fixed supervision targets. However, pretrained vision models organize information hierarchically, with different depths encoding complementary structural and semantic information, and the visual granularity most compatible with EEG may vary across subjects. To address this issue, we propose Subject-Aware Multi-Granularity Alignment (SAMGA), which makes visual-target construction an explicit part of EEG-visual alignment. SAMGA constructs adaptive visual supervision from multiple intermediate representations and models EEG-compatible visual granularity through a global granularity prior with subject-dependent residual calibration, enabling subject-aware training and subject-agnostic inference. Based on the resulting adaptive target, a coarse-to-fine alignment strategy first organizes global cross-modal geometry and then refines instance-level retrieval discrimination. On THINGS-EEG, SAMGA improves Top-1 retrieval accuracy over the strongest competing method by 8.7 percentage points under intra-subject evaluation and 12.0 percentage points under leave-one-subject-out evaluation. These results support a broader view of neural-visual alignment, in which performance depends not only on how neural representations are mapped, but also on what visual representations define their supervision.