AI Paper Atlas

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

Embedding Deep Metric for Person Re-identification: A Study Against Large Variations

Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, Stan Z. Li

ECCV 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 289 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 moderate positive mining on top of hard negative mining (ablation)Ours · CUHK03 validationrank-1 identification rateImproved
add hard negative mining and moderate positive mining over no mining (ablation)Ours · CUHK03 validationrank-1 identification rateImproved
train with metric layers instead of the softmax baseline (ablation)Ours · CUHK03 validationCMCImproved
use a moderate weight-constraint lambda instead of very large or near zero (ablation)Ours · CUHK03 validationrank-1 identification rateMixed
use untied weights between branches instead of tied weights with matched parameter count (ablation)Ours · CUHK03 validationrank-1 identification rateImproved
add Market1501 to the training dataOurs · CUHK01rank-1 identification rate (%): 69% -> 87%Improved

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