AI Paper Atlas

Research map / Detection and segmentation / CNN features

CrossDet: Crossline Representation for Object Detection

Heqian Qiu, Hongliang Li, Qingbo Wu, Jianhua Cui, Zichen Song, Lanxiao Wang, Minjian Zhang

ICCV 2021 · Detection and segmentation › CNN features · approach: Box regression and loss design · 22 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 crossline representation instead of center pointsCrossDet two-stage · PASCAL VOC2007 testAP: 48.4 -> 50.9Improved
use crossline representation instead of key pointsCrossDet two-stage · PASCAL VOC2007 testAP: 48.9 -> 50.9Improved
use crossline representation instead of anchor boxesCrossDet two-stage · PASCAL VOC2007 testAP: 49.3 -> 50.9Improved
add crossline extraction module (ablation)CrossDet · PASCAL VOC2007 testAP: 48.4 -> 50.9Improved
add axis-aware average pooling (ablation)CrossDet CEM · PASCAL VOC2007 testAP: 50.5 -> 50.9Improved
use global average pooling instead of none (ablation)CrossDet CEM · PASCAL VOC2007 testAP: 50.5 -> 50.5No clear effect
add soft-weighted crossline sampling (ablation)CrossDet CEM · PASCAL VOC2007 testAP: 48.8 -> 50.9Improved
use soft-weighted instead of max sampling (ablation)CrossDet CEM · PASCAL VOC2007 testAP: 50.7 -> 50.9Improved
add CEM to the classification branch only (ablation)CrossDet · PASCAL VOC2007 testAP: 48.4 -> 49.4Improved
add CEM to the regression branch only (ablation)CrossDet · PASCAL VOC2007 testAP: 48.4 -> 49.5Improved
add CEM on both branches (ablation)CrossDet · PASCAL VOC2007 testAP: 49.5 -> 50.9Improved
add decoupled regression (ablation)CrossDet · PASCAL VOC2007 testAP: 50.1 -> 50.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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