English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unsupervised domain adaptation person re-identification (Re-ID) aims toidentify pedestrian images within an unlabeled target domain with an auxiliarylabeled source-domain dataset. Many existing works attempt to recover reliableidentity information by considering multiple homogeneous networks. And takethese generated labels to train the model in the target domain. However, thesehomogeneous networks identify people in approximate subspaces and equallyexchange their knowledge with others or their mean net to improve theirability, inevitably limiting the scope of available knowledge and putting theminto the same mistake. This paper proposes a Dual-level Asymmetric MutualLearning method (DAML) to learn discriminative representations from a broaderknowledge scope with diverse embedding spaces. Specifically, two heterogeneousnetworks mutually learn knowledge from asymmetric subspaces through the pseudolabel generation in a hard distillation manner. The knowledge transfer betweentwo networks is based on an asymmetric mutual learning manner. The teachernetwork learns to identify both the target and source domain while adapting tothe target domain distribution based on the knowledge of the student.Meanwhile, the student network is trained on the target dataset and employs theground-truth label through the knowledge of the teacher. Extensive experimentsin Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiorityof DAML over state-of-the-arts.

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning