Metraipolis › archive › dc_855adf40b8fd

Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers — arXiv:2609.00358

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00358
License (as archived)
CC0-1.0
Archived
2026-10-17T07:10:27.896Z
SHA-256 of the archived text
2a566784820904d8ba5a53ebc84bb180df959c699406f5a200528ea96ee90b42
Stable URL of this page
https://metraipolis.com/documento/dc_855adf40b8fd

How to cite

Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers — arXiv:2609.00358 — arXiv (en), https://arxiv.org/abs/2609.00358 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_855adf40b8fd (Metraipolis archive dc_855adf40b8fd, sha256 2a566784820904d8ba5a53ebc84bb180df959c699406f5a200528ea96ee90b42)
BibTeX
@misc{dc855adf40b8fd,
  title = {Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers — arXiv:2609.00358},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00358},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_855adf40b8fd; sha256 2a566784820904d8ba5a53ebc84bb180df959c699406f5a200528ea96ee90b42},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00358. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision Transformers provide strong visual representations but typically rely on slowly updated parameters, limiting their ability to organize newly acquired information across different memory timescales. This work proposes \textit{Hierarchical Hebbian Memory}, a three-level memory architecture composed of rapid Working Memory, persistent Routed Episodic Memory, and slower Semantic Memory. A learned controller regulates memory contribution, read and write routing, plasticity, retention, and consolidation. A causal read-before-write lifecycle ensures that the current outcome cannot influence the prediction it supervises. The architecture is evaluated on Omniglot 5-way 1-shot recognition and CORe50 continual object recognition. With Swin-Tiny, the hierarchical model reaches 97.39\% accuracy on Omniglot and 95.37\% final accuracy on CORe50 when combined with experience replay. Learned multi-bank retrieval reaches 47.50\% delayed-association accuracy, compared with 24.17\% for a single persistent bank and 25.00\% without memory. After intervening distractors, Episodic Memory retains approximately 0.96 cosine similarity with stored associations, while Working Memory falls to approximately 0.05. These results show that Hebbian association and learned memory routing can jointly organize online visual experience across rapid, persistent, and consolidated memory timescales within Vision Transformers.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.00358 — 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 2026-10-17T07:00:58.898Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).