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

Domain adaptation helps generalizing object detection models to target domaindata with distribution shift. It is often achieved by adapting with access tothe whole target domain data. In a more realistic scenario, target distributionis often unpredictable until inference stage. This motivates us to exploreadapting an object detection model at test-time, a.k.a. test-time adaptation(TTA). In this work, we approach test-time adaptive object detection (TTAOD)from two perspective. First, we adopt a self-training paradigm to generatepseudo labeled objects with an exponential moving average model. The pseudolabels are further used to supervise adapting source domain model. Asself-training is prone to incorrect pseudo labels, we further incorporatealigning feature distributions at two output levels as regularizations toself-training. To validate the performance on TTAOD, we create benchmarks basedon three standard object detection datasets and adapt generic TTA methods toobject detection task. Extensive evaluations suggest our proposed method setsthe state-of-the-art on test-time adaptive object detection task.

STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization