AI Paper Atlas

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

Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain Mixup

Chuanchen Luo, Chunfeng Song, Zhaoxiang Zhang

ECCV 2020 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 118 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
replace camera-agnostic neighborhood loss with intra-camera loss (ablation)Ls + Lag · Duke→Marketrank-1 (%): 60.9 -> 70.6Improved
replace camera-agnostic neighborhood loss with intra-camera loss (ablation)Ls + Lag · Market→Dukerank-1 (%): 49.8 -> 70.0Improved
add inter-camera neighborhood loss Linter (ablation)Ls + Lintra · Duke→Marketrank-1 (%): 70.6 -> 81.2Improved
add inter-camera neighborhood loss Linter (ablation)Ls + Lintra · Market→Dukerank-1 (%): 70.0 -> 76.2Improved
add cross-domain mixup loss Lm in place of source classification (ablation)Ls + Lintra · Duke→Marketrank-1 (%): 70.6 -> 76.8Improved
add cross-domain mixup loss Lm in place of source classification (ablation)Ls + Lintra · Market→Dukerank-1 (%): 70.0 -> 73.7Improved
add cross-domain mixup loss Lm in place of source classification (ablation)Ls + Lintra + Linter · Duke→Marketrank-1 (%): 81.2 -> 88.1Improved
add cross-domain mixup loss Lm in place of source classification (ablation)Ls + Lintra + Linter · Market→Dukerank-1 (%): 76.2 -> 79.5Improved
raise scaling factor s from 10 to 14 (ablation)Ours · Duke→Marketrank-1 (%): 88.1 -> 74.4Hurt
lower scaling factor s from 10 to 6 (ablation)Ours · Duke→Marketrank-1 (%): 88.1 -> 80.3Hurt
vary Beta parameter alpha of mixup (ablation)Ours · Duke→Marketrank-1 (%): 86.7 -> 88.2No 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