AI Paper Atlas

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

Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding

Hong-Xing Yu, Ancong Wu, Wei‐Shi Zheng

TPAMI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 178 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
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · CUHK01 (single-shot)rank-1 (%): 55.95 -> 65.81Improved
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · CUHK03 (single-shot)rank-1 (%): 27.86 -> 38.27Improved
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · SYSU (single-shot)rank-1 (%): 25.38 -> 36.14Improved
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · Market-1501 (multi-shot)rank-1 (%): 49.94 -> 60.24Improved
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · ExMarket (multi-shot)rank-1 (%): 53.00 -> 62.98Improved
use asymmetric metric instead of symmetric metric (DECMEL) (ablation)DECAMEL · MSMT17 (multi-shot)rank-1 (%): 23.88 -> 30.34Improved
use asymmetric metric instead of symmetric metric (ablation)DECAMEL · SYSU (single-shot)S value (inter/intra): 1.61 -> 1.88Improved
add DECAMEL asymmetric metric clustering on top of JSTL featureJSTL feature · Market-1501 (multi-shot)mAP (%): 18.36 -> 32.44Improved
add DECAMEL on top of JSTL featureJSTL feature · CUHK01 (single-shot)rank-1 (%): 46.26 -> 65.81Improved
add DECAMEL on top of JSTL featureJSTL feature · MSMT17 (multi-shot)rank-1 (%): 21.24 -> 30.34Improved
use asymmetric metric clustering instead of symmetric clustering model UsNCAUsNCA · SYSU (single-shot)rank-1 (%): 21.07 -> 36.14Improved
set lambda to zero (remove cross-view consistency regularization) (ablation)DECAMEL · SYSUmatching rateHurt

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