Metraipolis › archive › dc_b061329794bb
Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval — arXiv:2608.19128
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19128
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:53:35.237Z
- SHA-256 of the archived text
d9b67c1b083479551328ee195f1d5329d4283a8e372324626ebf7222c863c505- Stable URL of this page
https://metraipolis.com/documento/dc_b061329794bb
How to cite
Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval — arXiv:2608.19128 — arXiv (en), https://arxiv.org/abs/2608.19128 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b061329794bb (Metraipolis archive dc_b061329794bb, sha256 d9b67c1b083479551328ee195f1d5329d4283a8e372324626ebf7222c863c505)
BibTeX
@misc{dcb061329794bb,
title = {Beyond Trial Averaging: Anchoring Neural and Visual Representations for Few-Repetition Brain-to-Image Retrieval — arXiv:2608.19128},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19128},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b061329794bb; sha256 d9b67c1b083479551328ee195f1d5329d4283a8e372324626ebf7222c863c505},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19128. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Decoding visual information from brain signals probes neural representations and enables neuro-rehabilitation and dream decoding. Recent brain-to-image retrieval approaches have achieved promising performance, typically by averaging many (up to 80) neural trials per image, requiring repeated stimulus presentation that increases latency, cost, and user burden. When only one or a few repetitions are available, the retrieval accuracy drops sharply. This drop is commonly attributed to query noise because averaging suppresses noise and increases signal stability. However, we find a non-transitive alignment pattern: the low-repetition query signal and the image representation each align with the high-repetition center, but not directly with each other. This pattern shows that query noise is only part of the problem and that gallery placement also affects retrieval. We therefore propose a neural-anchor-based retrieval (NEAR) framework that treats the high-repetition center as an anchor and approaches it from both sides: a denoiser pulls the noisy query toward the true anchor, and a small network predicts each candidate's pseudo anchor from its image and pulls the image toward it. Across four datasets spanning EEG, MEG and fMRI, NEAR consistently improved retrieval in the few-repetition regime. On THINGS-EEG2, it improved 200-way Top-1 accuracy by 5.7 and 9.3 percentage points respectively, when averaging one and four repetitions. By anchoring neural and visual representations, NEAR reduces reliance on repeated acquisition and brings neural retrieval closer to real-world deployment. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.19128 — 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 2026-10-18T13:50:58.963Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).