Metraipolis › archive › dc_09175ae1887e
Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation — arXiv:2608.12050
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12050
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T05:49:37.674Z
- SHA-256 of the archived text
fb1907223a07ed13aac0e6d4be194482ed764e8c6efd0b7f7ce61a538175d6f1- Stable URL of this page
https://metraipolis.com/documento/dc_09175ae1887e
How to cite
Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation — arXiv:2608.12050 — arXiv (en), https://arxiv.org/abs/2608.12050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09175ae1887e (Metraipolis archive dc_09175ae1887e, sha256 fb1907223a07ed13aac0e6d4be194482ed764e8c6efd0b7f7ce61a538175d6f1)
BibTeX
@misc{dc09175ae1887e,
title = {Predicting Functions, Not Features: KANs with Function-Space Joint-Embedding Predictive Learning for Medical Image Segmentation — arXiv:2608.12050},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12050},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09175ae1887e; sha256 fb1907223a07ed13aac0e6d4be194482ed764e8c6efd0b7f7ce61a538175d6f1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Kolmogorov--Arnold Networks (KANs) introduce explicit functional representations by parameterizing each network edge as a learnable univariate function. However, existing KAN-based segmentation models optimize edge functions only through objectives defined after edge aggregation, leaving individual functions without an explicit pre-aggregation learning target. To address this limitation, we propose Function-Space Joint-Embedding Predictive Learning (FS-JEPA) for medical image segmentation. Our FS-JEPA framework moves predictive learning into the pre-aggregation function space of KANs. A masked online branch predicts structured signatures of sampled KAN edge functions generated by a full-context exponential moving average target branch, while shared edge indices preserve correspondence between predictions and targets. Rather than predicting an isolated edge response, we represent each sampled edge function using a multi-radius signature composed of function evaluations around its input anchor. This structured representation captures local functional variations that cannot be characterized by a single response and provides a more informative predictive target. The function-space objective is jointly optimized with the segmentation loss during training, while the predictive branch is removed at inference. Experiments on five medical image segmentation benchmarks show that our FS-JEPA achieves the best average Dice and outperforms the strongest competing KAN-based method by +2.25 percentage points. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.12050 — 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 2026-10-19T05:42:25.906Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).