AI Paper Atlas

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

Deep Asymmetric Metric Learning via Rich Relationship Mining

Xinyi Xu, Yanhua Yang, Cheng Deng, Feng Zheng

CVPR 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 26 citations (OpenAlex)

Check 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 DAMLRRM instead of AMLdeep metric learning · CUB-200-2011 testR@1: 52.7 -> 55.1Improved
Use DAMLRRM instead of AMLdeep metric learning · Cars196 testR@1: 72.5 -> 73.5Improved
Use DAMLRRM instead of AMLdeep metric learning · Stanford Online Products testR@1: 66.3 -> 69.7Improved
Add asymmetric data streams and their shuffled loss (ablation)DAMLRRM · CUB-200-2011 testR@1: 52.3 -> 55.1Improved
Add graph loss with minimum-cost tree positive pairs (ablation)DAMLRRM · CUB-200-2011 testR@1: 52.3 -> 55.1Improved
Use minimum-cost spanning tree rather than fully combined positive pairs (ablation)graph-loss metric learning · CUB-200-2011 testR@1: 48.2 -> 51.2Improved
Set boundary α to 30 (ablation)DAMLRRM · CUB-200-2011 testR@1: 52.9 -> 55.1Improved
Set margin β to 0.5 (ablation)DAMLRRM · CUB-200-2011 testR@1: 51.9 -> 55.1Improved
Use DAMLRRM rather than one-stream Lifted or N-pair sampling (ablation)metric learning with limited sampling · CUB-200-2011 testR@1: 46.9 -> 52.3; 51.0 -> 52.3Improved
Use DAMLRRM instead of AMLdeep metric learning · Stanford Online Products testNMI: 89.1 -> 88.2Hurt
Use DAMLRRM instead of AMLdeep metric learning · Stanford Online Products testF1: 31.7 -> 30.5Hurt

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