Metraipolis › archive › dc_dea7b70bc27b
Understanding Clustering in Slot Attention via Particle Dynamics — arXiv:2610.04493
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04493
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:26:16.216Z
- SHA-256 of the archived text
4fee6b87b4fa75f1e206b37ceece15b6fa2f94f6c7827c9d2e00d79219cd186d- Stable URL of this page
https://metraipolis.com/documento/dc_dea7b70bc27b
How to cite
Understanding Clustering in Slot Attention via Particle Dynamics — arXiv:2610.04493 — arXiv, https://arxiv.org/abs/2610.04493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dea7b70bc27b (Metraipolis archive dc_dea7b70bc27b, sha256 4fee6b87b4fa75f1e206b37ceece15b6fa2f94f6c7827c9d2e00d79219cd186d)
BibTeX
@misc{dcdea7b70bc27b,
title = {Understanding Clustering in Slot Attention via Particle Dynamics — arXiv:2610.04493},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04493},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dea7b70bc27b; sha256 4fee6b87b4fa75f1e206b37ceece15b6fa2f94f6c7827c9d2e00d79219cd186d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Studying attention through the lens of interacting particle dynamics has shown how token clustering can emerge from the underlying dynamics. We extend this perspective to slot attention, a method for object-centric image segmentation and representation learning in which learned components obscure how much of the clustering behaviour is intrinsic to the attention dynamics. We therefore introduce simplified slot attention (SSA), a parameter-free variant whose dynamics are connected to soft $k$-means clustering and which provides a straightforward mechanistic explanation for the emergence of object-centric representations. On the Pascal VOC dataset, SSA achieves performance comparable to that of slot attention, demonstrating that competitive object-centric segmentation can be achieved without learned neural-network components. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.04493 — 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 2026-10-06T05:24:05.866Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).