Metraipolis › archive › dc_ea1e4e95f394

CoViG: Coarsened Vision GNN for Image Classification — arXiv:2610.21321

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.21321
License (as archived): CC0-1.0
Archived: 2026-10-16T10:35:15.853Z
SHA-256 of the archived text: b127f270d0a551fd80953b03e0092fc05bcd87ef3f53e4200de54d037bb6842b
Stable URL of this page: https://metraipolis.com/documento/dc_ea1e4e95f394

How to cite

CoViG: Coarsened Vision GNN for Image Classification — arXiv:2610.21321 — arXiv (en), https://arxiv.org/abs/2610.21321 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea1e4e95f394 (Metraipolis archive dc_ea1e4e95f394, sha256 b127f270d0a551fd80953b03e0092fc05bcd87ef3f53e4200de54d037bb6842b)

BibTeX

@misc{dcea1e4e95f394,
  title = {CoViG: Coarsened Vision GNN for Image Classification — arXiv:2610.21321},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21321},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea1e4e95f394; sha256 b127f270d0a551fd80953b03e0092fc05bcd87ef3f53e4200de54d037bb6842b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21321. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Although Graph Neural Networks are widely used in various domains, they remained mostly unexplored in computer vision. Convolutional Neural Networks and Vision Transformers were leading the field, until the quite recent introduction of Vision Graphs (ViG) that treat images as a set of nodes and apply graph convolution on their k-NN graphs. ViGs show impressive accuracy on image classification but their computational cost remains relatively high. Inspired by optimization methods for GNNs, we present CoViG, a novel approach combining graph coarsening and ViGs. Our method introduces an additional MinCUT pooling step within the Grapher component of intermediate ViG blocks. By simplifying the intermediate graphs and thus decreasing the number of nodes of specific blocks, our approach considerably reduces the computational cost of ViG during inference. We evaluated our approach on ImageNet with several ViG architectures, and we obtained accuracies equivalent to the original ViG models with only about 51\% of FLOPs.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21321 — 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 2026-10-16T08:52:02.651Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).