atlas

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

Unsupervised Person Re-Identification by Soft Multilabel Learning

CVPR 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 425 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 soft multilabel-guided hard negative mining with cross-view consistency and reference agent learningMAR · Market-1501rank-1: 62.2 -> 67.7Helped
Use soft multilabel-guided hard negative mining with cross-view consistency and reference agent learningMAR · DukeMTMC-reIDmAP: 27.2 -> 48.0Helped
Add soft multilabel-guided target-domain hard negative mining (ablation)MAR · Market-1501rank-1: 46.2 -> 67.7Helped
Replace feature-similarity guidance with soft multilabel guidance (ablation)hard negative mining · Market-1501rank-1: 44.4 -> 67.7Helped
Add cross-view consistent soft multilabel learning loss L_CML (ablation)MAR · Market-1501rank-1: 60.0 -> 67.7Helped
Add reference agent learning loss L_RAL (ablation)MAR · Market-1501mAP: 30.8 -> 40.0Helped
Add both cross-view consistency and reference agent learning losses (ablation)MAR · DukeMTMC-reIDrank-1: 60.1 -> 67.1Helped

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