Dataset Condensation Atlas

Application · The generator as the distilled artifact

MedSynth

MedSynth: Leveraging Generative Model for Healthcare Data Sharing

Renuga Kanagavelu

MICCAI 2024 · first public 2024-01-01

paper ↗catalogued✓ abstract read

In one paragraph

Condenses the knowledge in large medical datasets into a small generative model, combining an attention-based generator with a vision transformer so the model can produce a compact set of representative synthetic medical images; sharing the generator across hospitals avoids disclosing raw patient data. Reports outperforming state-of-the-art comparison methods and successfully defending against state-of-the-art membership-inference attacks.

Where it sits

BibTeX (generated; prefer the venue's official entry)
@article{kanagavelu2024medsynth,
  title   = {MedSynth: Leveraging Generative Model for Healthcare Data Sharing},
  author  = {Renuga Kanagavelu},
  journal = {MICCAI 2024},
  year    = {2024}
}

Nearby in The generator as the distilled artifact

2025-01

Point Cloud DD — Point Cloud Dataset Distillation

Deyu Bo, Xinchao Wang · ICML 2025notableOther datapaper ↗

2023-03

DiM — DiM: Distilling Dataset into Generative Model

Kai Wang, Jianyang Gu, Daquan Zhou et al. · arXiv 2023corepaper ↗code ↗

2019-12

GTN — Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data

Felipe Petroski Such, Aditya Rawal, Joel Lehman et al. · ICML 2020notablepaper ↗code ↗