AI Paper Atlas

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

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

Djebril Mekhazni, Amran Bhuiyan, George Ekladious, Eric Granger

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 139 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 between-class dissimilarity MMD loss to supervised loss (ablation)D-MMD · Duke to Marketrank-1 accuracy: 36.1 -> 51.8Improved
add within-class dissimilarity MMD loss to supervised loss (ablation)D-MMD · Duke to Marketrank-1 accuracy: 36.1 -> 45.8Improved
add within-class loss to between-class loss (ablation)D-MMD · Duke to Marketrank-1 accuracy: 51.8 -> 66.6Improved
add feature-based MMD loss to both dissimilarity losses (ablation)D-MMD · Duke to Marketrank-1 accuracy: 66.6 -> 70.6Improved
add feature-based MMD loss to both dissimilarity losses (ablation)D-MMD · Duke to MarketmAP: 45.4 -> 48.8Improved
add between-class loss to within-class loss (ablation)D-MMD · Market to Dukerank-1 accuracy: 30.3 -> 60.5Improved
add feature-based MMD loss to both dissimilarity losses (ablation)D-MMD · Market to Dukerank-1 accuracy: 60.5 -> 63.5Improved
add feature-based MMD loss to both dissimilarity losses (ablation)D-MMD · Market to DukemAP: 42.9 -> 46.0Improved
use between-class instead of within-class term alone (ablation)D-MMD · Market to Dukerank-1 accuracy: 30.3 -> 45.6Improved
use D-MMD instead of ECND-MMD · Duke to Marketrank-1 accuracy: 75.6 -> 70.6Hurt
use D-MMD instead of ECND-MMD · Duke to MarketmAP: 43.0 -> 48.8Improved
use D-MMD instead of BUCD-MMD · Market to Dukerank-1 accuracy: 47.4 -> 63.5Improved

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