AI Paper Atlas

Research map / Detection and segmentation / CNN features

CenterNet++ for Object Detection

Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, Qi Chuan Tian

TPAMI 2023 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 125 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 central region exploration (center keypoint branch) (ablation)CornerNet511-52 baseline · MS-COCO valAP: 37.6 -> 39.9Improved
add central region exploration (center keypoint branch) (ablation)CornerNet511-52 baseline · MS-COCO valAP large objects: 52.2 -> 52.3No clear effect
add center pooling to the central region exploration (ablation)CenterNet511-52 · MS-COCO valAP: 39.9 -> 40.8Improved
add center pooling (ablation)CenterNet511-52 · MS-COCO valAP large objects: 52.2 -> 53.6Improved
replace corner pooling with cascade corner pooling (ablation)CornerNet511-52 baseline · MS-COCO valAP: 37.6 -> 38.3Improved
replace corner pooling with cascade corner pooling (ablation)CenterNet511-52 · MS-COCO valAP: 40.8 -> 41.3Improved
replace corner pooling with cascade corner pooling (ablation)CornerNet511-52 baseline · MS-COCO valAP large objects: 52.2 vs 52.2No clear effect
use multi-resolution detection layers rather than a single-resolution output (ablation)MR-CenterNet R-50 · MS-COCO valAP: 40.9 -> 45.7Improved
add center keypoint modeling to CornerNet (SR-CenterNet vs CornerNet)HG-52 · MS-COCO test-devAP: 37.8 -> 41.6Improved
add center keypoint modeling to CornerNet, multi-scale testingHG-104 · MS-COCO test-devAP: 42.1 -> 47.0Improved
add center keypoint modeling to CornerNetHG-52/HG-104 · MS-COCO valaverage false discovery AF small boxes: decrease of 9.5% by CenterNet511-52 and 9.6% by CenterNet511-104Improved
replace predicted center keypoints with ground truthSR-CenterNet HG-52 · MS-COCO valAP: 41.3 -> 56.5Improved

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