Metraipolis › archive › dc_7f87b99ffbb7

Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks — arXiv:2608.19817

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.19817
License (as archived): CC0-1.0
Archived: 2026-10-18T12:04:40.886Z
SHA-256 of the archived text: 21832396761bcb2a9ed3e0702eae4cbfa76225340323ae8847d13d023999dd0c
Stable URL of this page: https://metraipolis.com/documento/dc_7f87b99ffbb7

How to cite

Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks — arXiv:2608.19817 — arXiv (en), https://arxiv.org/abs/2608.19817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f87b99ffbb7 (Metraipolis archive dc_7f87b99ffbb7, sha256 21832396761bcb2a9ed3e0702eae4cbfa76225340323ae8847d13d023999dd0c)

BibTeX

@misc{dc7f87b99ffbb7,
  title = {Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks — arXiv:2608.19817},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19817},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f87b99ffbb7; sha256 21832396761bcb2a9ed3e0702eae4cbfa76225340323ae8847d13d023999dd0c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures. Existing adaptive operators improve flexibility but often couple geometric scale variation with content-dependent filtering, while incurring high computational cost from per-location kernel generation. To decouple geometric scale adaptation from content-dependent filtering while avoiding expensive per-location kernel generation, we propose Continuous Relative-scale KAN (Core-KAN), a relative-scale-conditioned continuous convolution operator. Core-KAN maps input features into a compact latent basis space and uses a lightweight scale controller to predict local scales relative to an exponential moving average reference. A KAN-based generator represents depth-wise kernel bases as continuous coordinate functions, allowing the operator to synthesize spatial filters at arbitrary resolutions rather than being confined to a fixed lattice. Instead of synthesizing independent kernels at every location, it constructs a compact bank of scale-conditioned kernel responses and interpolates them according to the predicted local scale map. An independent mixing controller further combines the interpolated basis responses based on local content, explicitly decoupling geometric scale adaptation from content-dependent filtering. Together with lightweight pointwise projections, this design forms a low-rank dynamic convolution that scales efficiently with kernel size and integrates readily into hierarchical vision backbones. Experiments across three representative vision tasks show Core-KAN consistently outperforms strong convolutional and dynamic-kernel baselines with only marginal parameter and computational overhead, offering an efficient, general framework for continuous, scale-adaptive convolution.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.19817 — 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 2026-10-18T12:01:57.718Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).