AI Paper Atlas

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

Negative Samples Are at Large: Leveraging Hard-Distance Elastic Loss for Re-identification

Hyungtae Lee, Sungmin Eum, Heesung Kwon

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 10 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 HE loss instead of Triplet loss (ablation)re-ID baseline · VeRi-776mAP: 79.7 -> 80.6Improved
add MoReID dictionary with Triplet loss (ablation)re-ID baseline · VeRi-776mAP: 79.7 -> 79.4Hurt
combine MoReID with HE loss (ablation)re-ID baseline · VeRi-776mAP: 79.7 -> 83.3Improved
increase dictionary size from 1024 to 8192 with HE loss (ablation)MoReID · VeRi-776mAP: 81.9 -> 83.3Improved
increase dictionary size with Triplet losses (ablation)MoReID Tri-all · VeRi-776mAP: 79.7 -> 79.3No clear effect
raise momentum m from 0.9 to 0.997 (ablation)MoReID · VeRi-776mAP: 79.5 -> 83.3Improved
use batch configuration 16x16 instead of 128x2 (ablation)HE loss · VeRi-776mAP: 77.9 -> 83.3Improved
replace HE loss with N-pair loss (ablation)MoReID · VeRi-776mAP: 83.3 -> 79.8Hurt
replace HE loss with Ranked List loss (ablation)MoReID · VeRi-776mAP: 83.3 -> 80.5Hurt
replace HE loss with vanilla InfoNCE (ablation)MoReID · VeRi-776 (16x16)mAP: 83.3 -> 70.5Hurt
add hard mining to InfoNCE (ablation)InfoNCE · VeRi-776 (128x2)mAP: 62.9 -> 63.4Improved
add past positive samples to the dictionary (ablation)MoReID + HE loss · VeRi-776mAP: 83.3 -> 80.7Hurt

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