AI Paper Atlas

Research map / Detection and segmentation / CNN features

Gradient Corner Pooling for Keypoint-Based Object Detection

Xuyang Li, Xuemei Xie, Mingxuan Yu, Jiakai Luo, Chengwei Rao, Guangming Shi

AAAI 2023 · Detection and segmentation › CNN features · approach: Box regression and loss design · 1 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
Replace corner pooling with gradient corner poolingKeypoint-based object detectors · MS-COCOAP: 0.8%, 1.1%, 0.5%, 0.3%Improved
Replace CP with GCP (ablation)CornerNet-Saccade · MS-COCO val2017 arrayed objects subset (> 15)AP: 39.5 -> 46.0Improved
Replace CP with GCP (ablation)CornerNet-Saccade · MS-COCO val2017AP: 42.6 -> 42.8Improved
Add handcrafted convolution kernels after GCP (ablation)CornerNet-Saccade · MS-COCO val2017AP: 42.8 -> 43.3Improved
Replace center attention with corner attention (ablation)CornerNet-Saccade · MS-COCO val2017AR100: 62.1 -> 64.2Improved
Use top-left corner attention instead of center attention (ablation)CornerNet-Saccade attention maps · MS-COCO val2017AP att 30: 52.0 -> 52.8Improved
Use bottom-right corner attention instead of center attention (ablation)CornerNet-Saccade attention maps · MS-COCO val2017AP att 30: 52.0 -> 53.1Improved
Use both top-left and bottom-right corner attention maps instead of center attention (ablation)CornerNet-Saccade attention maps · MS-COCO val2017AP att 30: 52.0 -> 54.6Improved
Increase the maximum number of attention locations from 30 to 40 or 50 (ablation)CornerNet-Saccade attention mechanism · MS-COCO val2017AP att: 52.0; 52.0; 52.0No clear effect

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