AI Paper Atlas

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

GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set

Hanqing Chao, Kun Wang, Yiwei He, Junping Zhang, Jianfeng Feng

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 232 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
treat gait as an unordered set instead of averaging into a GEI (ablation)GaitSet · CASIA-B LT NMrank-1 accuracy: 89.0 -> 95.4Improved
treat gait as a set instead of GEI (ablation)GaitSet · CASIA-B LT CLrank-1 accuracy: 50.7 -> 69.9Improved
add MGP (multilayer global pipeline) (ablation)GaitSet · CASIA-B LTrank-1 accuracy: 95.4 -> 96.1 NM, 88.7 -> 90.8 BG, 69.9 -> 70.3 CLImproved
use max set pooling instead of mean (ablation)GaitSet · CASIA-B LT NMrank-1 accuracy: 95.0 -> 95.4Improved
use pixel-wise attention set pooling instead of max (ablation)GaitSet · CASIA-B LT NMrank-1 accuracy: 95.4 -> 95.6No clear effect
use independent HPM weights instead of shared (ablation)GaitSet · CASIA-B LTrank-1 accuracy: 91.1 -> 96.1 NM, 82.0 -> 90.8 BG, 60.9 -> 70.3 CLImproved
increase HPM scales from 1 to 5 (ablation)GaitSet · CASIA-B LTrank-1 accuracy: 91.8 -> 96.1 NM, 59.4 -> 70.3 CLImproved
add dropout to cross-entropy training (ablation)GaitSet · CASIA-B LT CLrank-1 accuracy: 46.7 -> 64.8Improved
add batch normalization to training (ablation)GaitSet · CASIA-B LTrank-1 accuracy: 94.4 -> 95.6 NM (CE loss)Improved
combine CE and triplet loss instead of either alone (ablation)GaitSet · CASIA-B LT NMrank-1 accuracy: 95.6 -> 96.1Improved
compress feature from 15,872 dims to 1024 with new FC (ablation)GaitSet · CASIA-B LT NMrank-1 accuracy: 96.1 -> 95.0No clear effect
reduce feature dimension too low (128) (ablation)GaitSet · CASIA-B LTrank-1 accuracy: 95.0 -> 91.7 NMHurt

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