AI Paper Atlas

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

Guided Saliency Feature Learning for Person Re-identification in Crowded Scenes

Lingxiao He, Wu Liu

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 127 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 mask layer to FCN baseline (ablation)FCN + average pooling · Crowd REID (trained on Market1501)rank-1 accuracy (%): 16.7 -> 32.2Improved
add pose layer to FCN baseline (ablation)FCN + average pooling · Crowd REID (trained on Market1501)rank-1 accuracy (%): 16.7 -> 30.0Improved
combine pose layer and mask layer (ablation)FCN + average pooling · Crowd REID (trained on Market1501)rank-1 accuracy (%): 16.7 -> 32.4Improved
add pose and mask layers (ablation)FCN + average pooling · Occluded REID (trained on Market1501)rank-1 accuracy (%): 60.2 -> 74.5Improved
add mask layer (ablation)FCN + average pooling · Market1501 (trained on Market1501)rank-1 accuracy (%): 94.8 -> 94.5No clear effect
add pose and mask layers (ablation)FCN + average pooling · Market1501 (trained on Market1501)rank-1 accuracy (%): 94.8 -> 95.3Improved
add pose and mask layers plus guided matchingFCN baseline · Market1501mAP (%): 83.4 -> 84.7Improved
add GASM to baseline for cross-domain transferResNet-50 baseline · Cross-domain Market1501 to MSMT17rank-1 accuracy (%): 22.2 -> 27.8Improved
add GASM to baseline for cross-domain transferResNet-50 baseline · Cross-domain DukeMTMC to Market1501rank-1 accuracy (%): 61.6 -> 67.2Improved
add GASM to baseline for cross-domain transferResNet-50 baseline · Cross-domain Market1501 to DukeMTMCrank-1 accuracy (%): 54.3 -> 56.4Improved
add GASM, trained on MSMT17ResNet-50 baseline · Crowd REID (trained on MSMT17)rank-1 accuracy (%): 44.0 -> 51.5Improved
compare GASM with FPRFPR · DukeMTMC-reIDrank-1 accuracy (%): 88.6 -> 88.3Hurt

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