AI Paper Atlas

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

A Simple and Effective Framework for Pairwise Deep Metric Learning

Qi Qi, Yan Yan, Zixuan Wu, Xiaoyu Wang, Tianbao Yang

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 16 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 DRO-KL_M sampling instead of MS losspairwise DML with BN-Inception · Cars-196Recall@1: 84.1 -> 86.4 (+2.3)Improved
use DRO-TopK_B instead of MS losspairwise DML · Cub-200-2011Recall@1: 65.7 -> 68.1 (+2.4)Improved
use DRO-TopK-PN_M instead of MS losspairwise DML · In-ShopRecall@1: 89.7 -> 91.3 (+1.6)Improved
use DRO-KL_M instead of best ensemble ABEpairwise DML · Cars-196Recall@1: 85.2 -> 86.4 (+1.2)Improved
lower gamma in grouped DRO-KL (generalized LS loss) from 1 to 0.001 (ablation)DRO-KL-G · Cars-196 (d=64)Recall@1: 70.5 -> 75.0Improved
lower gamma in grouped DRO-KL from 1 to 0.001 (ablation)DRO-KL-G · Cub-200-2011 (d=64)Recall@1: 56.4 -> 56.7No clear effect
lower gamma in grouped DRO-KL from 1 to 0.01 (ablation)DRO-KL-G · In-Shop (d=64)Recall@1: 84.8 -> 85.8Improved
DRO-KL-G gamma=1 versus LS loss (ablation)DRO-KL-G · Cars-196 (d=64)Recall@1: 69.7 -> 70.5No clear effect
generalized LS loss (gamma=0.001) instead of MS loss (ablation)DRO-KL-G · Cars-196 (d=64)Recall@1: 73.2 -> 75.0Improved
use DRO sampling instead of semi-hard or distance weighted sampling when positive:negative ratio falls (ablation)DRO variants · imbalance sweep, batch size 80 to 640Recall@1Improved
change embedding dimension from 1024 to 512 (ablation)DRO-TopK_M · In-Shop (PN ratio 0.006)Recall@1: 0.9046 -> 0.9058No clear effect

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