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

Person Re-Identification (re-ID) aims at retrieving images of the same persontaken by different cameras. A challenge for re-ID is the performancepreservation when a model is used on data of interest (target data) whichbelong to a different domain from the training data domain (source data).Unsupervised Domain Adaptation (UDA) is an interesting research direction forthis challenge as it avoids a costly annotation of the target data.Pseudo-labeling methods achieve the best results in UDA-based re-ID.Surprisingly, labeled source data are discarded after this initialization step.However, we believe that pseudo-labeling could further leverage the labeledsource data in order to improve the post-initialization training steps. Inorder to improve robustness against erroneous pseudo-labels, we advocate theexploitation of both labeled source data and pseudo-labeled target data duringall training iterations. To support our guideline, we introduce a frameworkwhich relies on a two-branch architecture optimizing classification and tripletloss based metric learning in source and target domains, respectively, in orderto allow \emph{adaptability to the target domain} while ensuring\emph{robustness to noisy pseudo-labels}. Indeed, shared low and mid-levelparameters benefit from the source classification and triplet loss signal whilehigh-level parameters of the target branch learn domain-specific features. Ourmethod is simple enough to be easily combined with existing pseudo-labeling UDAapproaches. We show experimentally that it is efficient and improvesperformance when the base method has no mechanism to deal with pseudo-labelnoise or for hard adaptation tasks. Our approach reaches state-of-the-artperformance when evaluated on commonly used datasets, Market-1501 andDukeMTMC-reID, and outperforms the state of the art when targeting the biggerand more challenging dataset MSMT.

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling