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

Small and cluttered objects are common in real-world which are challengingfor detection. The difficulty is further pronounced when the objects arerotated, as traditional detectors often routinely locate the objects inhorizontal bounding box such that the region of interest is contaminated withbackground or nearby interleaved objects. In this paper, we first innovativelyintroduce the idea of denoising to object detection. Instance-level denoisingon the feature map is performed to enhance the detection to small and clutteredobjects. To handle the rotation variation, we also add a novel IoU constantfactor to the smooth L1 loss to address the long standing boundary problem,which to our analysis, is mainly caused by the periodicity of angular (PoA) andexchangeability of edges (EoE). By combing these two features, our proposeddetector is termed as SCRDet++. Extensive experiments are performed on largeaerial images public datasets DOTA, DIOR, UCAS-AOD as well as natural imagedataset COCO, scene text dataset ICDAR2015, small traffic light dataset BSTLDand our released S$^2$TLD by this paper. The results show the effectiveness ofour approach. The released dataset S2TLD is made public available, whichcontains 5,786 images with 14,130 traffic light instances across fivecategories.

SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing