AI Paper Atlas

Research map / Detection and segmentation / CNN features

Anchor-Intermediate Detector: Decoupling and Coupling Bounding Boxes for Accurate Object Detection

Yilong Lv, Min Li, Yujie He, Shaopeng Li, Zhuzhen He, Aitao Yang

ICCV 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 11 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
attach corner-aware head in parallel after FPN rather than inside cls or reg branch (ablation)AID on RetinaNet R101 · COCO val2017 subsetAP: 39.4 -> 39.8Improved
increase corner loss weight lambda from 0.3 to 1 (ablation)AID on RetinaNet R101 · COCO val2017 subsetAP: 40.1 -> 38.2Hurt
add CoCl score (classification times corner score) in post-processing (ablation)AID · COCO val2017 subsetAP: 38.5 -> 39.8Improved
add BDC strategy on top of CoCl score (ablation)AID · COCO val2017 subsetAP: 39.8 -> 40.0Improved
average all corner points in BDC couple step (ablation)BDC · COCO val2017 subsetAP: 38.5 -> 36.0Hurt
use score-threshold corner selection instead of max or top-n (ablation)BDC · COCO val2017 subsetAP: 39.7 -> 40.0Improved
use avg, max or min of two corner heatmaps in CoCl score (ablation)CoCl score · COCO val2017 subsetAP: 39.8 / 39.6 / 39.6No clear effect
use only classification score without corner score in CoCl exponent form (ablation)CoCl score · COCO val2017 subsetAP: 39.9 -> 28.5Hurt
replace FPN with PAFPN (ablation)AID · COCO val2017 subsetAP: 40.0 -> 40.1Improved
replace MaxIoUAssigner with ATSSAssigner (ablation)AID · COCO val2017 subsetAP: 40.0 -> 40.6Improved
add AID to RetinaNet with ResNeXt-101-64x4dRetinaNet · COCO test-dev 1xAP: 41.4 -> 41.7Improved
add AID to GFLGFL · COCO test-devAP: +0.5 to +1.2Improved

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