AI Paper Atlas

Research map / Detection and segmentation / CNN features

Clustered Object Detection in Aerial Images

Fan Yang, Heng Fan, Peng Chu, Erik Blasch, Haibin Ling

ICCV 2019 · Detection and segmentation › CNN features · approach: Box regression and loss design · 531 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 cluster proposal network (CPNet) instead of even image partition (ablation)FRCNN+FPN ResNeXt101 · VisDrone valAP: 24.4 -> 27.6Improved
add CPNet instead of even image partition (fewer chips) (ablation)FRCNN+FPN+EIP · VisDrone valimages forwarded: 3,288 -> 1,945Improved
add ScaleNet to CPNet and DetecNet (ablation)DetecNet+CPNet ResNet50 · VisDrone valAP: 25.6 -> 26.7Improved
add ScaleNet to CPNet and DetecNet (ablation)DetecNet+CPNet ResNet101 · VisDrone valAP: 25.3 -> 26.7Improved
add ScaleNet to CPNet and DetecNet (ablation)DetecNet+CPNet ResNeXt101 · VisDrone valAP_s: 17.5 -> 19.1Improved
add ScaleNet (partition and padding) raises processed chips (ablation)DetecNet+CPNet ResNet50 · VisDrone valimages forwarded: 1,945 -> 2,716Hurt
add even image partition (EIP) at test timeFRCNN+FPN ResNet50 · VisDrone valAP_l: 54.7 -> 30.0Hurt
add even image partition (EIP) at test timeFRCNN+FPN ResNeXt101 · VisDrone valAP: 21.8 -> 24.4Improved
add even image partition (EIP) at test timeFRCNN+FPN ResNet50 · UAVDTAP: 11.0 -> 6.6Hurt
replace EIP with cluster-based crops (ClusDet)FRCNN+FPN ResNet50 · UAVDTAP: 6.6 -> 13.7Improved
raise TopN above 4 (ablation)ClusDet · VisDrone valAP: fluctuates around AP=27No clear effect
add multi-scale inference and box votingClusDet ResNeXt101 · VisDrone valAP: 28.4 -> 32.4Improved

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