AI Paper Atlas

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

Person Re-identification with Deep Similarity-Guided Graph Neural Network

Yantao Shen, Hongsheng Li, Shuai Yi, Dapeng Chen, Xiaogang Wang

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 341 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 SGGNN to the base model (ablation)siamese base model · Market-1501mAP (%): 76.4 -> 82.8Improved
add SGGNN to the base model (ablation)siamese base model · CUHK03mAP (%): 88.9 -> 94.3Improved
add SGGNN to the base model (ablation)siamese base model · DukeMTMCmAP (%): 61.8 -> 68.2Improved
add similarity guidance (SG) to SGGNN (ablation)SGGNN · Market-1501top-1 (%): 90.6 -> 92.3Improved
add similarity guidance (SG) to SGGNN (ablation)SGGNN · DukeMTMCmAP (%): 67.3 -> 68.2Improved
use SGGNN instead of k-reciprocal re-ranking (ablation)base model · Market-1501mAP (%): 78.5 -> 82.8Improved
use SGGNN instead of random walk (ablation)base model · DukeMTMCmAP (%): 66.0 -> 68.2Improved
add SGGNN training for l2 feature distance (ablation)base model · Market-1501 (l2 feature distance)mAP (%): 74.6 -> 76.7Improved
add SGGNN training for l2 feature distance (ablation)base model · CUHK03 (l2 feature distance)top-1 (%): 91.0 -> 93.6Improved
reduce top-K from 100 to 50 (ablation)SGGNN · DukeMTMCmAP (%): 68.2 -> 66.6Hurt
increase top-K from 100 to 150 (ablation)SGGNN · DukeMTMCmAP (%): 68.2 -> 71.8Improved
change number of message passing steps K from 4 to 3 or 5 (ablation)SGGNN · Market-1501mAP (%): 82.8 -> 82.0Hurt

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