AI Paper Atlas

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

EMD Metric Learning

Zizhao Zhang, Yubo Zhang, Xibin Zhao, Yue Gao

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 9 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
Learn EMD metric (EMD-M) instead of traditional EMD, 20% trainingEMD · TWITTERaccuracy: +5.48%Improved
Learn EMD metric (EMD-M) instead of traditional EMD, 30% trainingEMD · TWITTERaccuracy: +6.83%Improved
Learn EMD metric (EMD-M) instead of traditional EMD, 40% trainingEMD · TWITTERaccuracy: +8.32%Improved
Learn EMD metric (EMD-M) instead of traditional EMD, 50% trainingEMD · TWITTERaccuracy: +8.5%Improved
EMD-M versus PML with 50% training dataPML · TWITTERaccuracy: +5.29%Improved
EMD-M versus CDL with 50% training dataCDL · TWITTERaccuracy: +3.98%Improved
EMD-M versus CDL_PLS with 50% training dataCDL_PLS · TWITTERaccuracy: +2.74%Improved
Increase number of imposters ki beyond about 10 (ablation)EMD-M · NTUaccuracyNo clear effect
Set lambda away from 0.5 (NTU) or 0.2 (TWITTER), too small or too large (ablation)EMD-M · NTU and TWITTERaccuracyHurt
Alternate updates of metric A and flow F (ablation)EMD-M · NTU and TWITTERobjective valueImproved

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