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

This paper presents our proposed methods for domain adaptive pedestrianre-identification (Re-ID) task in Visual Domain Adaptation Challenge(VisDA-2020). Considering the large gap between the source domain and targetdomain, we focused on solving two biases that influenced the performance ondomain adaptive pedestrian Re-ID and proposed a two-stage training procedure.At the first stage, a baseline model is trained with images transferred fromsource domain to target domain and from single camera to multiple camerastyles. Then we introduced a domain adaptation framework to train the model onsource data and target data simultaneously. Different pseudo label generationstrategies are adopted to continuously improve the discriminative ability ofthe model. Finally, with multiple models ensembled and additional postprocessing approaches adopted, our methods achieve 76.56% mAP and 84.25% rank-1on the test set. Codes are available athttps://github.com/vimar-gu/Bias-Eliminate-DA-ReID

1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification