AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Privacy-Preserving Adaptive Re-Identification without Image Transfer

Hamza Rami, Jhony H. Giraldo, Nicolas Winckler, Stéphane Lathuilière

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
add MMD loss with Gaussian kernel to local client training (ablation)Fed-Protoid · MS->MarketmAP: 42.6 -> 51.0Improved
use linear kernel MMD instead of no MMD (ablation)Fed-Protoid · MS->MarketmAP: 42.6 -> 38.1Hurt
use order-2 kernel MMD instead of no MMD (ablation)Fed-Protoid · MS->CUHK03-npmAP: 22.4 -> 13.1Hurt
add teacher-student framework to the pseudo-client (ablation)Fed-Protoid · MS->MarketmAP: 37.4 -> 51.0Improved
transmit teacher instead of student models for aggregation (ablation)Fed-Protoid · MS->MarketmAP: 49.3 -> 51.0Improved
compute source prototypes with the global model instead of the pseudo-client model (ablation)Fed-Protoid · MS->MarketmAP: 43.1 -> 51.0Improved
compute source prototypes with the global model (ViT variant) (ablation)Fed-Protoid++ · MS->MarketmAP: 60.5 -> 61.7Improved
replace ResNet-50 with ViT-S (both ImageNet pretrained) (ablation)Fed-Protoid · MS->CUHK03-npmAP: 23.8 -> 27.5Improved
use ViT with LUPerson self-supervised pretraining instead of ResNet-50 ImageNet (ablation)Fed-Protoid · MS->MarketmAP: 51 -> 61.7Improved
subsample source prototypes uniformly (ablation)Fed-Protoid · RP->MarketmAPNo clear effect

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