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

Object detection at night is a challenging problem due to the absence ofnight image annotations. Despite several domain adaptation methods, achievinghigh-precision results remains an issue. False-positive error propagation isstill observed in methods using the well-established student-teacher framework,particularly for small-scale and low-light objects. This paper proposes atwo-phase consistency unsupervised domain adaptation network, 2PCNet, toaddress these issues. The network employs high-confidence bounding-boxpredictions from the teacher in the first phase and appends them to thestudent's region proposals for the teacher to re-evaluate in the second phase,resulting in a combination of high and low confidence pseudo-labels. The nightimages and pseudo-labels are scaled-down before being used as input to thestudent, providing stronger small-scale pseudo-labels. To address errors thatarise from low-light regions and other night-related attributes in images, wepropose a night-specific augmentation pipeline called NightAug. This pipelineinvolves applying random augmentations, such as glare, blur, and noise, todaytime images. Experiments on publicly available datasets demonstrate that ourmethod achieves superior results to state-of-the-art methods by 20\%, and tosupervised models trained directly on the target data.

2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection