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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Due to the lack of labels and the domain diversities, it is a challenge tostudy person re-identification in the cross-domain setting. An admirable methodis to optimize the target model by assigning pseudo-labels for unlabeledsamples through clustering. Usually, attributed to the domain gaps, thepre-trained source domain model cannot extract appropriate target domainfeatures, which will dramatically affect the clustering performance and theaccuracy of pseudo-labels. Extensive label noise will lead to sub-optimalsolutions doubtlessly. To solve these problems, we propose an Anti-NoiseLearning (ANL) approach, which contains two modules. The Feature DistributionAlignment (FDA) module is designed to gather the id-related samples anddisperse id-unrelated samples, through the camera-wise contrastive learning andadversarial adaptation. Creating a friendly cross-feature foundation forclustering that is to reduce clustering noise. Besides, the Reliable SampleSelection (RSS) module utilizes an Auxiliary Model to correct noisy labels andselect reliable samples for the Main Model. In order to effectively utilize theoutlier information generated by the clustering algorithm and RSS module, wetrain these samples at the instance-level. The experiments demonstrate that ourproposed ANL framework can effectively reduce the domain conflicts andalleviate the influence of noisy samples, as well as superior performancecompared with the state-of-the-art methods.

ANL: Anti-Noise Learning for Cross-Domain Person Re-Identification