Metraipolis › archive › dc_331c75e64cf7
RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG — arXiv:2609.31698
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31698
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:50:27.944Z
- SHA-256 of the archived text
6b60432488d84dadbb24f25d19d39c1e3b505b98a75a6cde82d03fe208e485d3- Stable URL of this page
https://metraipolis.com/documento/dc_331c75e64cf7
How to cite
RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG — arXiv:2609.31698 — arXiv (en), https://arxiv.org/abs/2609.31698 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_331c75e64cf7 (Metraipolis archive dc_331c75e64cf7, sha256 6b60432488d84dadbb24f25d19d39c1e3b505b98a75a6cde82d03fe208e485d3)
BibTeX
@misc{dc331c75e64cf7,
title = {RPA: Residual Patch-Token Adapter for Image Retrieval from EEG and MEG — arXiv:2609.31698},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31698},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_331c75e64cf7; sha256 6b60432488d84dadbb24f25d19d39c1e3b505b98a75a6cde82d03fe208e485d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31698. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most existing MEG and EEG (M/EEG) visual decoding methods align brain signals with a single global embedding extracted from a pretrained visual encoder, leaving open whether intermediate patch representations, which preserve richer and more granular rich visual information, can improve representation learning. To address this question, we introduce the Residual Patch Adapter (RPA), a lightweight, modular adapter that leverages all patch tokens from an intermediate layer of a ViT visual encoder for alignment. Through extensive ablation analyses, we first show that pooling or masking patch tokens degrades the learned representation, demonstrating that retaining the full set of patch tokens is important for EEG alignment, while the CLS token provides little unique information. We then use a series of six quantitative feature analyses to show that both higher-level semantics and lower-level visual features, including color and texture, are essential for this EEG-to-image alignment. Under current protocols, our system achieves Top-1 accuracies of 95.4\% within-subject and 35.5\% cross-subject on THINGS-EEG2, and 65.2\% and 6.7\%, respectively, on THINGS-MEG, achieving state-of-the-art (SOTA) performance across both datasets. Evaluations with alternative brain encoders, including pretrained EEG foundation models, demonstrate that the approach extends beyond the projection-based EEG encoder. Furthermore, we provide a plug-and-play interface that allows RPA to be replaced by convolution, attention, or ConvNeXt alternatives. Together, these findings provide significant insight into M/EEG-to-image representation learning by establishing design principles for leveraging the latent space of visual encoders, and open new directions for brain--image alignment and non-invasive brain--computer interface (BCI). Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.31698 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T23:29:26.875Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).