AI Paper Atlas

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

A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification

Pirazh Khorramshahi, Amit Kumar, Neehar Peri, Sai Saketh Rambhatla, Jun-Cheng Chen, Rama Chellappa

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 258 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 the orientation-conditioned key-point attention branch to ResNet-101ResNet-101 baseline · VeRi-776mAP: 55.75 -> 61.18Improved
add the orientation-conditioned key-point attention branch to ResNet-50ResNet-50 baseline · VeRi-776mAP: 52.88 -> 58.52Improved
add the attention branch to ResNet-101ResNet-101 baseline · VehicleID (test size 800)CMC@1: 70.03 -> 74.69Improved
add the attention branch to ResNet-101ResNet-101 baseline · VehicleID (test size 2400)CMC@1: 59.04 -> 63.54Improved
add the attention branch to ResNet-101ResNet-101 baseline · VeRi-Wild (Large)mAP: 38.99 -> 41.68Improved
add re-ranking post-processingAAVER (ResNet-101) · VeRi-776mAP: 61.18 -> 66.35Improved
add two-branch design instead of single branch with heatmaps concatenated (ablation)AAVER (ResNet-101) · VeRi-776mAP: 0.528 -> 0.612Improved
add two-branch design instead of single branch (ablation)AAVER (ResNet-101) · VehicleID (test size 800)CMC@1: 69.61 -> 74.69Improved
add adaptive key-point selection instead of combining all heatmaps (ablation)AAVER (ResNet-101) · VeRi-776CMC@1: 87.66 -> 88.97Improved
add adaptive key-point selection instead of combining all heatmaps (ablation)AAVER (ResNet-101) · VehicleID (test size 800)CMC@1: 71.79 -> 74.69Improved
pool shallow (56x56, Res2) rather than deeper (14x14) global features (ablation)AAVER (ResNet-101) · VeRi-776CMC@1: 85.88 -> 88.97Improved
pool shallow (56x56) rather than 28x28 global features (ablation)AAVER (ResNet-101) · VeRi-776mAP: 0.608 -> 0.612Improved

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