AI Paper Atlas

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

Cross-View Asymmetric Metric Learning for Unsupervised Person Re-Identification

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

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 342 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 asymmetric view-specific projections instead of a symmetric metric (ablation)CAMEL · VIPeR (single-shot)rank-1 accuracy: 27.5 -> 30.9Improved
add asymmetric view-specific projections instead of a symmetric metric (ablation)CAMEL · CUHK01 (multi-shot)rank-1 accuracy: 54.9 -> 61.9Improved
add asymmetric view-specific projections instead of a symmetric metric (ablation)CAMEL · Market-1501 (multi-shot)rank-1 accuracy: 47.6 -> 54.5Improved
add asymmetric view-specific projections instead of a symmetric metric (ablation)CAMEL · ExMarket (multi-shot)rank-1 accuracy: 48.7 -> 55.9Improved
add asymmetric view-specific projections instead of a symmetric metric (ablation)CAMEL · CUHK03 (single-shot)rank-1 accuracy: 29.8 -> 31.9Improved
increase number of clusters K from 500 to 1250 (ablation)CAMEL · CUHK01 (single-shot)rank-1 accuracy: 57.35 -> 52.75Hurt
vary number of clusters K from 250 to 1250 (ablation)CAMEL · Market-1501 (multi-shot)rank-1 accuracy: 54.48 -> 54.48No clear effect
run alternating optimization to convergence (K=500) (ablation)CAMEL · CUHK01 clusteringrate of clusters with multiple persons: 57.0% -> 34.3%Improved
replace cluster pseudo-labels with true labels (supervised CAMEL_s)CAMEL · CUHK03 (single-shot)rank-1 accuracy: 31.9 -> 45.1Improved
use CAMEL on LOMO features instead of L2 distanceCAMEL · VIPeR (single-shot, LOMO)rank-1 accuracy: 11.6 -> 26.4Improved
use CAMEL instead of Dic on JSTL featuresCAMEL · CUHK01 (single-shot)rank-1 accuracy: 49.3 -> 57.3Improved

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