AI Paper Atlas

Research map / Detection and segmentation / CNN features

Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai

TPAMI 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 1,065 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add divide-and-conquer selection by obliquity factor r (ablation)Gliding Vertex · DOTA (IoU 0.5) with FPNmAP (%): 74.43 -> 75.02Improved
Add divide-and-conquer selection by obliquity factor r (ablation)Gliding Vertex · DOTA (IoU 0.5) w/o FPNmAP (%): 72.33 -> 73.39Improved
Add divide-and-conquer selection by obliquity factor r (ablation)Gliding Vertex · DOTA (IoU 0.7) with FPNmAP (%): 50.94 -> 53.49Improved
Gliding vertex representation instead of RBox regressionFaster R-CNN with FPN · DOTA (IoU 0.5)mAP (%): 68.72 -> 75.02Improved
Gliding vertex representation instead of direct Vertex regressionFaster R-CNN with FPN · DOTA (IoU 0.5)mAP (%): 63.65 -> 75.02Improved
Gliding vertex instead of RBox regression at stricter IoU 0.7Faster R-CNN with FPN · DOTA (IoU 0.7)mAP (%): 27.56 -> 53.49Improved
Add FPN to Gliding Vertex (ablation)Gliding Vertex · DOTA (IoU 0.5)mAP (%): 73.39 -> 75.02Improved
Raise obliquity threshold t_r from 0.65 to 0.85 (ablation)Gliding Vertex with FPN · DOTAmAP (%): 73.29 -> 75.06Improved
Raise obliquity threshold t_r from 0.85 to 0.95 (ablation)Gliding Vertex with FPN · DOTAmAP (%): 75.06 -> 74.44Hurt
Use multi-scale testGliding Vertex · RCTW-17F-measure (%): 68.1 -> 69.3Improved
Swap Faster R-CNN head for light-head R-CNN (ablation)Gliding Vertex · DOTA (FPN)mAP (%): 75.02 -> 74.05Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy