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

Rotation detection is a challenging task due to the difficulties of locatingthe multi-angle objects and separating them effectively from the background.Though considerable progress has been made, for practical settings, there stillexist challenges for rotating objects with large aspect ratio, densedistribution and category extremely imbalance. In this paper, we propose anend-to-end refined single-stage rotation detector for fast and accurate objectdetection by using a progressive regression approach from coarse to finegranularity. Considering the shortcoming of feature misalignment in existingrefined single-stage detector, we design a feature refinement module to improvedetection performance by getting more accurate features. The key idea offeature refinement module is to re-encode the position information of thecurrent refined bounding box to the corresponding feature points throughpixel-wise feature interpolation to realize feature reconstruction andalignment. For more accurate rotation estimation, an approximate SkewIoU lossis proposed to solve the problem that the calculation of SkewIoU is notderivable. Experiments on three popular remote sensing public datasets DOTA,HRSC2016, UCAS-AOD as well as one scene text dataset ICDAR2015 show theeffectiveness of our approach. Tensorflow and Pytorch version codes areavailable at https://github.com/Thinklab-SJTU/R3Det_Tensorflow andhttps://github.com/SJTU-Thinklab-Det/r3det-on-mmdetection, and R3Det is alsointegrated in our open source rotation detection benchmark:https://github.com/yangxue0827/RotationDetection.

R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object