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

Test-time adaptation methods have been gaining attention recently as apractical solution for addressing source-to-target domain gaps by graduallyupdating the model without requiring labels on the target data. In this paper,we propose a method of test-time adaptation for category-level object poseestimation called TTA-COPE. We design a pose ensemble approach with aself-training loss using pose-aware confidence. Unlike previous unsuperviseddomain adaptation methods for category-level object pose estimation, ourapproach processes the test data in a sequential, online manner, and it doesnot require access to the source domain at runtime. Extensive experimentalresults demonstrate that the proposed pose ensemble and the self-training lossimprove category-level object pose performance during test time under bothsemi-supervised and unsupervised settings. Project page:https://taeyeop.com/ttacope

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation