AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders

Qi Wang, Zeyu Zhang, Dong Wang, Di Gai, Xin Xiong, Jiyang Xu, Ruihua Zhou

ICCV 2025 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation · 3 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 historical distillation (Pa) to baseline MAE (ablation)VehicleMAE baseline · VeRi-776 unsupervisedmAP: 37.6 -> 40.1Improved
add present distillation (Pr) to baseline MAE (ablation)VehicleMAE baseline · VeRi-776 unsupervisedmAP: 37.6 -> 40.5Improved
add all modules (PPMD and VMIM) to baseline MAE (ablation)VehicleMAE · VeRi-776 unsupervisedmAP: 37.6 -> 42.5Improved
add all modules (PPMD and VMIM) to baseline MAE (ablation)VehicleMAE · VehicleID large unsupervisedRank-1: 69.0 -> 73.3Improved
use asymmetric instead of random mask sampling at 75% mask ratio (ablation)VehicleMAE · VeRi-776 unsupervisedmAP: 40.1 -> 42.5Improved
use asymmetric instead of random mask sampling at 25% mask ratio (ablation)VehicleMAE · VeRi-776 unsupervisedmAP: 38.8 -> 40.6Improved
use asymmetric instead of random mask sampling at 50% mask ratio (ablation)VehicleMAE · VeRi-776 unsupervisedmAP: 39.2 -> 41.7Improved
raise asymmetric mask ratio from 25% to 75% (ablation)VehicleMAE · VeRi-776 unsupervisedmAP: 40.6 -> 42.5Improved
combine historical and present distillation vs independent MAEs (mean encoder) (ablation)VehicleMAE · VeRi-776 unsupervisedRank-1: 84.6 -> 87.6Improved
combine historical and present distillation vs independent MAEs (mean encoder) (ablation)VehicleMAE · VehicleID unsupervisedRank-1: 70.9 -> 73.3Improved
average two encoders into a mean encoder instead of using one encoder (ablation)VehicleMAE · VeRi-776 unsupervisedRank-1: 84.3 -> 84.6Improved
pre-train with VehicleMAE on DiffVERI instead of CMAECLIP-B/16 · VeRi-776 unsupervisedmAP: 41.6 -> 42.5Improved

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