AI Paper Atlas

Research map / Detection and segmentation / CNN features

Hilbert Curve-Encoded Rotation-Equivariant Oriented Object Detector with Locality-Preserving Spatial Mapping

Qi Ming, Liuqian Wang, Juan Fang, Xudong Zhao, Yucheng Xu, Ziyi Teng, Yue Zhou, Xiaoxi Hu, Xiaohan Zhang, Yufei Guo

AAAI 2026 · Detection and segmentation › CNN features · approach: Box regression and loss design · 2 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 Hilbert curve traversal convolution (HCTConv) to multi-scale features (ablation)two-stage oriented detector baseline · DOTA valmAP (%): 67.5 -> 69.1Improved
add HPFormer cross-scale attention after HCTConv (ablation)HERO-Det · DOTA valmAP (%): 69.1 -> 70.2Improved
add Residual Oriented Response Network (RORN) for regression (ablation)baseline detector · DOTA valmAP (%): 67.5 -> 68.6Improved
add Hilbert circular shifting (HCS) for rotation-invariant classification (ablation)RORN detector · DOTA valmAP (%): 68.6 -> 69.2Improved
flatten features with raster scan and apply 1x9 conv instead of 3x3 conv (ablation)baseline detector · DOTA valmAP (%): 67.5 -> 67.2No clear effect
use Hilbert curve instead of Z-order or Peano curve for convolution scan path (ablation)HCTConv · DOTA valmAP (%): 68.0 (Z-order), 64.0 (Peano) -> 69.1Improved
use Peano curve scan path (ablation)HCTConv · DOTA valmAP (%): 67.5 -> 64.0Hurt
enlarge Hilbert conv kernel from 1x7 to 1x9 (ablation)HCTConv · DOTA valmAP (%): 68.8 -> 69.1Improved
replace naive ORN with RORN (dense residual, continuous angles) (ablation)OAPH · DOTA valmAP (%): 67.1 -> 67.5Improved
add Hilbert curve unfolding on top of RORN (ablation)OAPH · DOTA valmAP (%): 67.5 -> 68.6Improved
use Hilbert curve for both flattening and reconstruction instead of raster scan (ablation)HPFormer · DOTA valmAP (%): 67.2 -> 69.1Improved
increase HCS shifting count n from 0 to 3 (ablation)HCS · DOTA val, bridge (BR)AP (%): 43.1 -> 44.3Improved

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