AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Ruihang Chu, Yifan Sun, Yadong Li, Zheng Liu, Chi Zhang, Yichen Wei

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 213 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 viewpoint-aware two-branch metric learningtriplet baseline · VehicleID smalltop1: 75.23 -> 83.26Improved
add viewpoint-aware two-branch metric learningtriplet baseline · Veri-776mAP: 58.75 -> 66.34Improved
add cross-space constraint L_cross (ablation)VANet · VehicleID smalltop1: 70.23 -> 83.26Improved
add cross-space constraint L_cross (ablation)VANet · Veri-776mAP: 43.32 -> 66.34Improved
add within-space constraints L_s and L_d (ablation)VANet · VehicleID smalltop1: 81.20 -> 83.26Improved
add within-space constraints L_s and L_d (ablation)VANet · Veri-776mAP: 63.22 -> 66.34Improved
use VANet instead of baseline for D-view true matchestriplet baseline · VehicleID smalltop1_d: 33.53 -> 59.85Improved
use VANet instead of baseline with S-view distractors removedtriplet baseline · VehicleID smalltop1_d*: 56.09 -> 67.67Improved
remove S-view gallery images (easier condition)baseline · VehicleID smallD-view top1: 33.53 -> 56.09Improved
add cross-space constraint L_cross to remove S-view distraction failure (ablation)VANet · VehicleID smalltop1_d: 13.59 -> 59.85Improved
add viewpoint prediction errors (error rate 0.1) (ablation)VANet · VehicleID smalltop1: 83.26 -> 77.63Hurt
use 3 branches instead of 2 (ablation)VANet · VehicleID smalltop1: 83.26 -> 83.01No 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