AI Paper Atlas

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

Heterogeneous Relational Complement for Vehicle Re-Identification

Jiajian Zhao, Yifan Zhao, Jia Li, Ke Yan, Yonghong Tian

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 79 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 cross-level branch to the regional-only model (ablation)HRCN · VeRi-776mAP: 0.807 -> 0.831Improved
add regional branch to the cross-level-only model (ablation)HRCN · VeRi-776mAP: 0.814 -> 0.831Improved
use graph relation module instead of concatenation (ablation)HRCN · VeRi-776mAP: 0.803 -> 0.831Improved
fuse bottom-top rather than into one unified graph (ablation)HRCN · VeRi-776mAP: 0.803 -> 0.831Improved
add stage 3 features as lower-level complement (ablation)HRCN · VeRi-776mAP: 0.819 -> 0.825Improved
add stage 2 features as well as stage 3 (ablation)HRCN · VeRi-776mAP: 0.825 -> 0.831Improved
progressive center pooling instead of grid partition (ablation)HRCN · VeRi-776mAP: 0.817 -> 0.831Improved
progressive center pooling instead of vertical partition (ablation)HRCN · VeRi-776mAP: 0.818 -> 0.831Improved
progressive center pooling instead of horizontal partition (ablation)HRCN · VeRi-776mAP: 0.822 -> 0.831Improved
use full HRCN instead of plain baselineResNet-50-ibn-a baseline · VeRi-776mAP: 0.768 -> 0.831Improved
HRCN versus PVEN with extra annotationsHRCN · VERI-Wild SmallCMC@1: 0.967 -> 0.940Hurt
HRCN versus PVEN on mCGM benchmarkHRCN · VeRi-776 benchmarkmCGM: 0.560 -> 0.630Improved

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