首页|Transferring discriminative knowledge via connective momentum clustering on person re-identification
Transferring discriminative knowledge via connective momentum clustering on person re-identification
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NSTL
Elsevier
Unsupervised domain adaptation in person re-identification remains a challenge to learning discrimina-tive representations due to the absence of labels in target domain. Clustering could provide pseudo-labels, but the limitation mainly comes from imperfect clustering and noisy pseudo-labels. To address this draw-back, we propose Connective Momentum Clustering (CMC) framework to build a connection estimator via graph convolutional networks to transfer rich connection knowledge from the annotation space of source data to target domain. It estimates connections from context to reveal relationship between unlabeled data and helps to discover more reliable clusters. With momentum mechanism, stable pseudo-labels are updated iteratively with confidence and refined consistently to encourage more discriminative networks. Meanwhile, we notice that the huge domain gap between source and target domains results in severe pollution in BatchNorm layers. To tackle this problem, we normalize the data stream separately to de-couple different distribution and further boost the performance in target domain. We adopt our CMC framework on mainstream tasks and achieves 80.2% mAP / 91.3% Rank-1 on Duke -> Market task and 70.4% mAP / 82.4% Rank-1 on Market -> Duke task. (C) 2022 Elsevier Ltd. All rights reserved.
Person re-identificationUnsupervised domain adaptationGraph convolutional networksMomentum mechanismBatch normalization
NSTL
Elsevier
