AI Paper Atlas

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

End-to-End Deep Kronecker-Product Matching for Person Re-Identification

Yantao Shen, Tong Xiao, Hongsheng Li, Shuai Yi, Xiaogang Wang

CVPR 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 159 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 KPM with soft feature warping (ablation)Baseline ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 68.8 -> 70.6; 82.9 -> 85.5; 55.5 -> 56.0Improved
Remove soft warping after KPM (ablation)Baseline+KPM · Market-1501, CUHK03, DukeMTMCmAP: 68.8 -> 62.6; 82.9 -> 71.7; 55.5 -> 50.8Hurt
Add residual self-attention (ablation)Baseline+KPM · Market-1501, CUHK03, DukeMTMCmAP: 70.6 -> 72.0; 85.5 -> 86.2; 56.0 -> 58.1Improved
Add hourglass multi-scale features (ablation)Baseline ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 68.8 -> 69.9; 82.9 -> 84.1; 55.5 -> 60.4Improved
Use separate scale losses and average scale confidences instead of concatenating scale features (ablation)Baseline+HG · Market-1501mAP: 69.9 -> 69.1Hurt
Combine KPM, residual self-attention, and hourglass features (ablation)Baseline ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 68.8 -> 75.3; 82.9 -> 89.2; 55.5 -> 63.2Improved
Use difference verification loss rather than cross-entropy, OIM, or triplet loss (ablation)Base ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 59.8, 60.9, 67.9 -> 68.8; 62.7, 72.5, 80.7 -> 82.9; 40.7, 47.7, 54.6 -> 55.5Improved
Use 2:1 rather than 1:1 image aspect ratio with random initialization (ablation)Base ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 30.2 -> 32.4; 60.8 -> 61.5; 23.2 -> 24.9Improved
Replace elementwise square with absolute value (ablation)Base ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: +1.9%, +1.2%, +0.9%Hurt
Move elementwise square before global average pooling (ablation)Base ResNet-50 · Market-1501, CUHK03, DukeMTMCmAP: 68.8 -> 64.3; 82.9 -> 72.7; 55.5 -> 50.9Hurt
Remove elementwise square (ablation)Base ResNet-50 · Person re-identificationconvergenceHurt
Remove subtraction and elementwise square, and concatenate image-pair features (ablation)Base ResNet-50 · Person re-identificationconvergenceHurt

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