AI Paper Atlas

Research map / Detection and segmentation / CNN features

Enriched Feature Guided Refinement Network for Object Detection

Jing Nie, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 97 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 feature enrichment scheme (ablation)SSD VGG16 320 · PASCAL VOC 2007mAP: 77.2 -> 79.4Improved
add cascaded refinement scheme (ablation)SSD VGG16 320 · PASCAL VOC 2007mAP: 77.2 -> 81.0Improved
add feature enrichment scheme (ablation)SSD VGG16 320 · MS COCO minivalAP: 24.4 -> 29.1Improved
add cascaded refinement scheme (ablation)SSD VGG16 320 · MS COCO minivalAP: 24.4 -> 31.1Improved
combine both schemes (full EFGRNet) (ablation)SSD VGG16 320 · MS COCO minivalAP: 24.4 -> 33.0Improved
combine both schemes (full EFGRNet) (ablation)SSD VGG16 320 · PASCAL VOC 2007mAP: 77.2 -> 81.4Improved
add second dilated branch to MSCF (r=1,2) (ablation)MSCF · PASCAL VOC 2007mAP: 78.7 -> 79.0Improved
add third dilated branch (r=4) to MSCF (ablation)MSCF · PASCAL VOC 2007mAP: 79.0 -> 79.4Improved
add more branches with other dilation rates beyond three (ablation)MSCF · PASCAL VOC 2007mAPNo clear effect
use standard deformable convolution offsets instead of dilated convolution (ablation)FGRM · PASCAL VOC 2007mAP: 80.2 -> 80.5Improved
generate deformable offsets from B1x position offsets (dx,dy) instead of feature-based offsets (ablation)FGRM · PASCAL VOC 2007mAP: 80.5 -> 81.0Improved
use only scale offsets (dh,dw) from B1x for deformable offsets (ablation)FGRM · PASCAL VOC 2007mAP: 81.0 -> 80.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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