Research map / 3D vision / 3D generation
ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ME-GAN rather than WGAN-GP for disease-conditioned ECG synthesis | Tianchi w/ diseases overall · Tianchi w/ diseases overall | rFID: 7.534 -> 3.722 | Helped |
| Use ME-GAN rather than CBL-GAN for disease-conditioned ECG synthesis | Tianchi LAD · Tianchi LAD | rFID: 5.322 -> 2.662 | Helped |
| Use ME-GAN rather than CBL-GAN for disease-conditioned ECG synthesis | Tianchi RBBB · Tianchi RBBB | rFID: 3.471 -> 1.491 | Helped |
| Use ME-GAN rather than CBL-GAN for disease-conditioned ECG synthesis | Tianchi RAD · Tianchi RAD | rFID: 5.573 -> 3.433 | Helped |
| Use ME-GAN rather than SMDCGAN without disease conditions | Tianchi w/o diseases · Tianchi w/o diseases overall | rFID: 2.618 -> 2.343 | Helped |
| Use ME-GAN rather than WGAN-GP without disease conditions | PTB w/o diseases · PTB w/o diseases overall | rFID: 42.046 -> 15.282 | Helped |
| Augment training data with ME-GAN samples | 1D ResNet-34 disease classifier · Tianchi disease classification | Mean PR-AUC: 0.879 -> 0.902 | Helped |
| Replace MixupNorm with self-modulation (ablation) | ME-GAN · Tianchi w/ diseases | PR-AUC: 0.902 -> 0.858 | Hurt |
| Replace MixupNorm with self-modulation (ablation) | ME-GAN · Tianchi w/ diseases | rFID: 3.722 -> 5.432 | Hurt |
| Add the view discriminator (ablation) | ME-GAN · Tianchi w/ diseases | PR-AUC: 0.867 -> 0.902 | Helped |
| Add the view discriminator (ablation) | ME-GAN · Tianchi w/ diseases | rFID: 5.212 -> 3.722 | Helped |
| Add the auxiliary classifier (ablation) | ME-GAN · Tianchi w/ diseases | PR-AUC: 0.895 -> 0.902 | Helped |
Closest papers by meaning
- Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning (AAAI 2024 · similarity 0.85)
- Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals (NeurIPS 2024 · similarity 0.85)
- Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners (ICML 2025 · similarity 0.84)
- Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram (ICLR 2024 · similarity 0.83)
- GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images (NeurIPS 2025 · similarity 0.83)
- Parallel-Learning of Invariant and Tempo-variant Attributes of Single-Lead Cardiac Signals: PLITA (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.