AI Paper Atlas

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

Robust Person Re-Identification by Modelling Feature Uncertainty

Tianyuan Yu, Da Li, Yongxin Yang, Timothy M. Hospedales, Tao Xiang

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Cross-modality and occlusion re-identification · 152 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
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · Market-1501, 20% random label noisemAP: 45.36 -> 53.40Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · CUHK01, 10% random label noisemAP: 52.02 -> 63.36Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · CUHK03, 50% random label noisemAP: 6.44 -> 10.61Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · Market-1501, 10% patterned label noisemAP: 25.87 -> 27.04Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · CUHK01, 10% patterned label noisemAP: 42.87 -> 52.72Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · CUHK03, 10% patterned label noisemAP: 10.10 -> 10.87Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · Market-1501, closed-world, no added noisemAP: 67.66 -> 70.82Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · CUHK01, closed-world, no added noisemAP: 60.70 -> 70.70Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · DukeMTMC-ReID, closed-world, no added noisemAP: 54.17 -> 55.98Improved
model each feature as a Gaussian with learned variance (DistributionNet)ResNet50 ReID model · Market-1501 open-world set verification, FTR 0.1%TTR: 43.03 -> 55.76Improved
use CleanNet with 10% clean reference set and removal of 20% suspected noisy samples instead of baselineResNet-Baseline · Market-1501, 20% random label noisemAP: 45.36 -> 44.22Hurt
add Bootstrap hard label refinementResNet-Baseline · Market-1501, closed-world, no added noisemAP: 67.66 -> 69.09Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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