AI Paper Atlas

Research map / Detection and segmentation / CNN features

Adaptive Rotated Convolution for Rotated Object Detection

Yifan Pu, Yiru Wang, Zhuofan Xia, Yizeng Han, Yulin Wang, Weihao Gan, Zidong Wang, Shiji Song, Gao Huang

ICCV 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 228 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
replace static convolutions with adaptive rotated convolution (ARC) in the backboneOriented R-CNN ResNet-50 · DOTA-v1.0 single-scalemAP: 75.81 -> 77.35Improved
use ARC backbone across detectorsRotated RetinaNet, R3Det, S2ANet, Rotated Faster R-CNN, CFA · DOTA-v1.0mAP: +3.03, +2.62, +1.36, +1.60, +4.16 mAPImproved
use ARC backbone across detectors on HRSC2016Rotated RetinaNet, S2ANet, Oriented R-CNN · HRSC2016mAP: +1.27, +2.12, +1.84 mAPImproved
add adaptive kernel rotation versus static convolution (ablation)Oriented R-CNN · DOTA-v1.0mAP: 75.81 -> 76.97Improved
increase number of kernels from 1 to 4 (conditional computation) (ablation)ARC-R50 · DOTA-v1.0mAP: 76.97 -> 77.35Improved
increase number of kernels from 4 to 6 (ablation)ARC-R50 · DOTA-v1.0mAP: 77.35 -> 77.38No clear effect
replace convolutions in more backbone stages with ARC (ablation)ARC-R50 · DOTA-v1.0mAP: 77.17 -> 77.35Improved
add spatial information encoding in routing function (ablation)ARC routing function · DOTA-v1.0mAP: 76.41 -> 76.80Improved
add adaptive combination of kernel weights in routing function (ablation)ARC routing function · DOTA-v1.0mAP: 76.41 -> 76.98Improved
use ARC with four kernels instead of static ResNet-50Oriented R-CNN · DOTA-v1.0 inference speedFPS: 29.9 -> 29.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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