Metraipolis › archive › dc_852ea305395d

A Hybrid CNN--State-Space--Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification — arXiv:2609.29376

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29376
License (as archived)
CC0-1.0
Archived
2026-10-08T06:44:27.880Z
SHA-256 of the archived text
329e0cb7453feb52922c26b7ab00ced75f901f5a0ad8df36caed4245a2de7b8a
Stable URL of this page
https://metraipolis.com/documento/dc_852ea305395d

How to cite

A Hybrid CNN--State-Space--Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification — arXiv:2609.29376 — arXiv (en), https://arxiv.org/abs/2609.29376 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_852ea305395d (Metraipolis archive dc_852ea305395d, sha256 329e0cb7453feb52922c26b7ab00ced75f901f5a0ad8df36caed4245a2de7b8a)
BibTeX
@misc{dc852ea305395d,
  title = {A Hybrid CNN--State-Space--Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification — arXiv:2609.29376},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29376},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_852ea305395d; sha256 329e0cb7453feb52922c26b7ab00ced75f901f5a0ad8df36caed4245a2de7b8a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29376. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automatic 12-lead electrocardiogram (ECG) classification requires representations that jointly capture local waveform morphology, long-range temporal dynamics, and cross-lead dependencies, yet integrating these properties within a single efficient architecture remains challenging. This paper introduces a hybrid CNN-SSM-Attention backbone for 12-lead ECG classification. A convolutional stem performs early waveform tokenization and temporal reduction, mixed state-space and depthwise-convolutional blocks model temporal dynamics and local morphology, and a late self-attention stage enables global token interaction at reduced resolution. To improve transfer from unlabeled data, we further develop an ECG-oriented Joint-Embedding Predictive Pretraining (JEPA) framework. Unlike ViT-based JEPA methods that mask patch tokens before the encoder, the proposed method samples span masks at the latent temporal resolution and projects them back to the waveform domain, then predicts clean latent targets from a momentum encoder without waveform reconstruction. Experiments on CPSC2018, Chapman-Shaoxing, and PTB-XL, with pretraining on approximately 350K unlabeled CODE-15 recordings, show that the proposed backbone provides strong supervised baselines under a compact parameter budget. JEPA pretraining further improves transfer, particularly in reduced-label settings and under both full fine-tuning and LoRA-based adaptation. Code: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.29376 — 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 2026-10-08T06:09:29.846Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).