AI Paper Atlas

Research map / Detection and segmentation / CNN features

Large Selective Kernel Network for Remote Sensing Object Detection

Yuxuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng, Jian Yang, Xiang Li

ICCV 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 1,034 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
decompose a large kernel into two depth-wise kernels instead of one single kernel (ablation)LSKNet-T · DOTA-v1.0mAP / FPS: 80.66 -> 80.91 mAP; 18.6 -> 20.5 FPSImproved
decompose into three kernels rather than two (ablation)LSKNet-T · DOTA-v1.0mAP / FPS: 80.91 -> 80.77 mAP; 20.5 -> 19.2 FPSHurt
use spatial kernel selection rather than none (ablation)LSKNet-T · DOTA-v1.0mAP: 80.94 -> 81.31Improved
use channel selection (SKNet-style) instead of spatial selection (ablation)LSKNet-T · DOTA-v1.0mAP: 81.31 -> 80.57Hurt
use receptive field of 23 instead of 11 or 39 (ablation)LSKNet-T · DOTA-v1.0mAP: 80.80 (RF 11), 80.84 (RF 39) -> 80.94 (RF 23)Improved
use both max and average pooling in spatial selection (ablation)LSKNet-T · DOTA-v1.0mAP: 81.23 (max), 81.12 (avg) -> 81.31Improved
replace ResNet-18 backbone with LSKNet-T across detection frameworksOriented RCNN, RoI Transformer, S2A-Net, R3Det · DOTA-v1.0mAP: 79.27 -> 81.31 (O-RCNN); 74.16 -> 78.39 (R3Det)Improved
use LSKNet-S instead of other large kernel or selective attention backbonesOriented RCNN · DOTA-v1.0mAP: 81.15 (VAN-B1) -> 81.48Improved
use LSKNet-S backbone vs O-RCNN with prior bestOriented RCNN · FAIR1M-v1.0mAP: 45.60 -> 47.87Improved

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