atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination

CVPR 2022 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated medical and multimodal learning · 13 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Use a pretrained StyleGAN2 visual prior instead of learning the generator from scratch (ablation)VPGAN · VIS-THRank-1: 52.85 -> 76.19Helped
Add MSCA to the encoder (ablation)VPGAN · VIS-THRank-1: 71.90 -> 76.19Helped
Use federated training with MPR rather than FedProxVPFL · Global Test Avg.Rank-1: 61.98 -> 69.80Helped
Add Model Proximity Regularization (ablation)VPFL · Global Test Avg.Rank-1: 66.49 -> 69.80Helped
Use federated training rather than training one local-only model per institutionVPFL · Global Test Avg.Rank-1: Local Only C1: 38.41; VPFL: 69.80Helped
Fuse the outputs of independently trained local modelsFused strategy · Global Test Avg.Rank-1: 37.39Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy