AI Paper Atlas

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

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

Boqiang Xu, Jian Liang, Lingxiao He, Zhenan Sun

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Generalizable person re-identification · 61 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 global branch (IN layers) (ablation)META · Protocol-3 (C3/MS/M)mAP: mAP drops 20.7%, 14.1% and 32.4% without itImproved
add expert branch (domain-specific BN) (ablation)META · Protocol-3 (C3/MS/M)mAP: mAP drops 13.5%, 3.9% and 4.6% without itImproved
add learnable aggregation module (ablation)META · Protocol-3 (C3/MS/M)mAP: gains of 1.1%, 1.1% and 1.4%; Rank-1 62.0 -> 62.9Improved
use BN-IN design instead of BN-BN global branch (ablation)Global branch · Protocol-3 (C3/MS/M)Rank-1: 60.0 -> 62.9Improved
use BN-IN design instead of BN-IBN global branch (ablation)Global branch · Protocol-3 (C3/MS/M)Rank-1: 61.3 -> 62.9Improved
use BN-IN design instead of IN-IN global branch (ablation)Global branch · Protocol-3 (C3/MS/M)Rank-1: 57.6 -> 62.9Improved
add consistency loss for aggregation module (ablation)META · Protocol-3 (target MSMT17)mAP: 21.2 -> 24.4; Rank-1 48.4 -> 52.1Improved
use L_consis instead of cross-entropy loss for aggregation (ablation)META · Protocol-3 (target MSMT17)Rank-1: 50.9 -> 52.1Improved
use L_consis instead of triplet loss for aggregation (ablation)META · Protocol-3 (target MSMT17)Rank-1: 50.4 -> 52.1Improved
concatenate F-exp with F-global at test time (ablation)META · Protocol-3 (target C3)mAP: 46.9 -> 47.1No clear effect
use only F-exp instead of concatenated feature (ablation)META · Protocol-3 (target MSMT17)mAP: 24.4 -> 10.2Hurt

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