TU Darmstadt (Rohr, Reich, Hoog Antink et al.)
Dual-encoder single-lead ECG classifier for atrial fibrillation detection that fuses a raw-signal branch with a spectrogram branch via axial attention and a Transformer. Originally developed as a graduate-course project at TU Darmstadt for the 2017 PhysioNet/CinC Challenge, and later extended in a 2023 follow-up study. Released in four sizes up to 130M parameters (S/M/L/XL), alongside a simpler CNN+LSTM variant.
Architecture
Hybrid
Dual-branch network combining a raw-signal encoder and a spectrogram encoder, fused via axial attention and a Transformer ('DualNet++'); a CNN+LSTM 'DualNet' variant is also released, in S/M/L/XL sizes up to 130M parameters
Framework
PyTorch
Added to catalog
2026-07-10
MIT
License for model weights only. Associated code may be licensed seperately, check code source for specific terms.
11,000 subjects with continuous single-lead ECG recorded over up to two weeks; used for unsupervised/self-supervised arrhythmia-representation pretraining.
Short single-lead ECG recordings (9-61s) labeled as normal, AF, other rhythm, or noisy.
AF classification (challenge setting, pretrained)