AI Paper Atlas

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

Spectral Feature Transformation for Person Re-Identification

Chuanchen Luo, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 164 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 spectral feature transformation (SFT) to the baseline (ablation)AM-Softmax ResNet-50 baseline · CUHK03 (labeled)mAP / Rank-1: 40.6 -> 60.2 mAP; 44.9 -> 66.3 Rank-1Improved
add SFT to the baseline (ablation)AM-Softmax ResNet-50 baseline · Market-1501mAP / Rank-1: 77.3 -> 79.6 mAP; 91.2 -> 91.6 Rank-1Improved
add SFT to the baseline (ablation)AM-Softmax ResNet-50 baseline · MSMT17mAP / Rank-1: 37.3 -> 44.7 mAP; 66.7 -> 71.9 Rank-1Improved
add deep supervision with a shared classifier on the original feature (ablation)SFT · Market-1501mAP / Rank-1: 79.6 -> 82.7 mAP; 91.6 -> 93.4 Rank-1Improved
add deep supervision with a shared classifier on the original feature (ablation)SFT · MSMT17mAP / Rank-1: 44.7 -> 47.6 mAP; 71.9 -> 73.6 Rank-1Improved
share the classifier between original and transformed features instead of using an unshared one (ablation)SFT + deep supervision · MSMT17mAP / Rank-1: 35.3 -> 47.6 mAP; 63.7 -> 73.6 Rank-1Improved
share the classifier between original and transformed features instead of using an unshared one (ablation)SFT + deep supervision · Market-1501mAP / Rank-1: 79.0 -> 82.7 mAP; 91.8 -> 93.4 Rank-1Improved
add proposed top-n post-processing (ablation)SFT + deep supervision · Market-1501mAP / Rank-1: 82.7 -> 87.5 mAP; 93.4 -> 94.1 Rank-1Improved
add proposed top-n post-processing (ablation)SFT + deep supervision · CUHK03 (labeled)mAP / Rank-1: 62.4 -> 71.7 mAP; 68.2 -> 74.3 Rank-1Improved
use k-reciprocal re-ranking instead of proposed post-processingSFT + deep supervision · Market-1501mAP / Rank-1: 87.5 -> 90.6 mAP; 94.1 -> 93.5 Rank-1Mixed
replace Ncut loss with SFTsame ResNet-50 backbone · CUHK03 (labeled)mAP / Rank-1: 40.3 -> 62.4 mAP; 45.5 -> 68.2 Rank-1Improved
replace Ncut loss with SFTsame ResNet-50 backbone · Market-1501mAP / Rank-1: 79.5 -> 82.7 mAP; 92.0 -> 93.4 Rank-1Improved

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