AI Paper Atlas

Research map / Detection and segmentation / CNN features

BorderDet: Border Feature for Dense Object Detection

Han Qiu, Yuchen Ma, Zeming Li, Songtao Liu, Jian Sun

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design

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 Border Alignment Module on classification branch (ablation)FCOS · COCO minivalAP: 38.6 -> 39.7Improved
add Border Alignment Module on regression branch (ablation)FCOS · COCO minivalAP90: 16.0 -> 18.6Improved
add BAM on both branches (ablation)FCOS · COCO minivalAP: 38.6 -> 41.4Improved
add BAM on classification branch (ablation)FCOS · COCO minivalAP90: 16.0 -> 15.9No clear effect
use border-sensitive feature maps instead of border-agnostic (ablation)BorderDet · COCO minivalAP: 40.8 to 41.4Improved
use channel-wise max-pooling instead of channel-wise average-pooling (ablation)BorderAlign · COCO minivalAP: 40.6 -> 41.4Improved
use channel-wise instead of border-wise aggregation (max-pooling) (ablation)BorderAlign · COCO minivalAP: 39.5 -> 41.4Improved
pooling size 10 instead of 0 (iterative box prediction) (ablation)BorderAlign · COCO minivalAP: 39.0 -> 41.4Improved
increase pooling size from 10 to 32 (ablation)BorderAlign · COCO minivalAP: 41.4 -> 41.4No clear effect
replace BorderAlign with RoIAlign (ablation)BorderDet · COCO minivalAP: 41.4 -> 40.4Hurt
replace BorderAlign with deformable convolution (ablation)BorderDet · COCO minivalAP: 41.4 -> 39.5Hurt
add region features to single point feature (ablation)FCOS · COCO minivalAP: 38.9 -> 39.9Improved

Later papers that compared with this method

2 later accepted papers report BorderDet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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