AI Paper Atlas

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

Domain Adaptation through Synthesis for Unsupervised Person Re-identification

Slawomir Bak, Peter Carr, Jean-Francois Lalonde

ECCV 2018 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 231 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 SyRI synthetic images to real training data (ablation)joint re-id model · PRID2011rank-1: 7.0 -> 15.0Improved
add SyRI synthetic images to real training data (ablation)joint re-id model · Market-1501rank-1: 44.7 -> 54.3Improved
add SyRI synthetic images to real training data (ablation)joint re-id model · VIPeRrank-1: 32.3 -> 36.4Improved
add SyRI synthetic images to real training data (ablation)joint re-id model · iLIDSrank-1: 51.0 -> 54.8Mixed
add plain CycleGAN translation without regularization (ablation)R + S · iLIDSrank-1: 54.8 -> 53.9Hurt
add identity mapping loss Lid to CycleGAN (ablation)CycleGAN · PRID2011rank-1: 33.0 -> 40.0Improved
replace Lid with LRef (ablation)CycleGAN + Lid · CUHK01rank-1: 54.0 -> 48.4Hurt
replace Lid with LRef (ablation)CycleGAN + Lid · PRID2011rank-1: 40.0 -> 28.0Hurt
add foreground mask loss (ablation)CycleGAN + LRef · PRID2011rank-1: 28.0 -> 43.0Improved
add foreground mask loss (ablation)CycleGAN + LRef · Market-1501rank-1: 57.5 -> 65.7Improved
add illumination inference instead of random domain selection (ablation)domain translation · PRID2011rank-1: 36.0 -> 43.0Improved
add illumination inference instead of random domain selection (ablation)domain translation · VIPeRrank-1: 38.9 -> 43.0Improved

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