Metraipolis › archive › dc_d96e29dbad8e

Robust Transfer Learning for Paper ECG Recognition — arXiv:2609.39581

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39581
License (as archived)
CC0-1.0
Archived
2026-10-07T12:45:33.352Z
SHA-256 of the archived text
33e3a5fa0fd0bf26d72336c283a24efc485092d7b24a3ce9e458f658c3f0227a
Stable URL of this page
https://metraipolis.com/documento/dc_d96e29dbad8e

How to cite

Robust Transfer Learning for Paper ECG Recognition — arXiv:2609.39581 — arXiv (en), https://arxiv.org/abs/2609.39581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d96e29dbad8e (Metraipolis archive dc_d96e29dbad8e, sha256 33e3a5fa0fd0bf26d72336c283a24efc485092d7b24a3ce9e458f658c3f0227a)
BibTeX
@misc{dcd96e29dbad8e,
  title = {Robust Transfer Learning for Paper ECG Recognition — arXiv:2609.39581},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39581},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d96e29dbad8e; sha256 33e3a5fa0fd0bf26d72336c283a24efc485092d7b24a3ce9e458f658c3f0227a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Paper ECG recognition is challenging because real-world ECG images vary in layout, physical artifacts, and label availability. We introduce RobECG-CL, a rank-aware contrastive learning framework for robust paper ECG representation learning. Starting from standard 12-lead ECG recordings, we construct progressively degraded paper ECG views with heterogeneous layouts and train the model to balance same-recording invariance with degradation-aware ordering. Across synthetic stress tests on CODE-II and EchoNext, RobECG-CL improves robustness under severe degradation and few-shot transfer, outperforming contrastive learning baselines and surpassing the waveform-based foundation model, ECG-FM, in the 1% labeled setting. On 312 samples of hospital data with 37 labels, RobECG-CL achieves the best macro AUROC.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39581 — 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 2026-10-07T12:14:14.111Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).