AI Paper Atlas

Research map / Detection and segmentation / CNN features

PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection

Xinhao Cai, Liulei Li, Gensheng Pei, Zeren Sun, Yazhou Yao, Wenguan Wang

ECCV 2026 · Detection and segmentation › CNN features · approach: Box regression and loss design · 5 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
use hybrid strip+square kernels instead of dense-only (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 78.57 -> 80.11Improved
use hybrid kernels instead of strip-only (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.62 -> 80.11Improved
use hybrid kernels instead of sparse-only (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.36 -> 80.11Improved
dilations (1,3,3,3) instead of (1,1,1,1) (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.88 -> 80.11Improved
larger dilations (1,4,4,4) vs default (1,3,3,3) (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 80.11 -> 80.01Hurt
dilations (1,2,2,2) vs default (1,3,3,3) (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.98 -> 80.11Hurt
increase parallel DW branches from 1 to 5 (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.62 -> 80.11Improved
increase parallel DW branches from 4 to 5 (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 79.99 -> 80.11Improved
apply HKR re-parameterization (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)FPS: 43.4 -> 54.6Improved
apply HKR re-parameterization (ablation)PKINet-v2-T · DOTA-v1.0 (ablation, 100-epoch pretraining)FPS: 46.2 -> 58.0Improved
apply HKR re-parameterization (ablation)PKINet-v2-S · DOTA-v1.0 (ablation, 100-epoch pretraining)mAP: 80.11 -> 80.11No clear effect
swap ResNet-50 for PKINet-v2-S backboneR3Det · DOTA-v1.0 (different detectors)mAP: 69.70 -> 77.64Improved

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