AI Paper Atlas

Research map / Detection and segmentation / CNN features

GraphFPN: Graph Feature Pyramid Network for Object Detection

Gangming Zhao, Weifeng Ge, Yizhou Yu

ICCV 2021 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 164 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 first group of contextual layers (CGL-1) (ablation)GraphFPN · MS-COCO 2017 valAP: 38.2 -> 39.1Improved
add second group of contextual layers (CGL-2) (ablation)GraphFPN · MS-COCO 2017 valAP: 38.7 -> 39.1Improved
add hierarchical layers to contextual-only layers (ablation)GraphFPN · MS-COCO 2017 valAP: 37.2 -> 39.1Improved
add contextual layers to hierarchical-only layers (ablation)GraphFPN · MS-COCO 2017 valAP: 36.2 -> 39.1Improved
add spatial self-attention (ablation)GraphFPN · MS-COCO 2017 valAP: 37.8 -> 39.1Improved
add local channel-wise attention (ablation)GraphFPN · MS-COCO 2017 valAP: 37.9 -> 39.1Improved
add local channel self-attention (ablation)GraphFPN · MS-COCO 2017 valAP: 37.6 -> 39.1Improved
add both local channel attentions (ablation)GraphFPN · MS-COCO 2017 valAP: 37.1 -> 39.1Improved
increase layers per group from 1 to 3 (ablation)GraphFPN · MS-COCO 2017 valAP: 36.1 -> 39.1Improved
increase layers per group from 3 to 5 (ablation)GraphFPN · MS-COCO 2017 valAP: 39.1 -> 37.1Hurt
add GraphFPN to Faster R-CNN+FPNFaster R-CNN+FPN · MS-COCO 2017 test-devAP: 36.2 -> 43.7Improved
add multi-scale training and augmented head to GraphFPNGraphFPN · MS-COCO 2017 test-devAP: 42.1 -> 43.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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