AI Paper Atlas

Research map / Detection and segmentation / CNN features

Soft Anchor-Point Object Detection

Chenchen Zhu, Fangyi Chen, Zhiqiang Shen, Marios Savvides

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 192 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 soft-weighted anchor points (down-weight points near box boundaries) (ablation)FSAF · COCO val2017AP: 35.9 -> 37.0Improved
add soft-weighted anchor points (ablation)FSAF · COCO val2017AP75: 37.9 -> 39.5Improved
add soft-selected pyramid levels on top of soft weighting (ablation)FSAF + SW · COCO val2017AP: 37.0 -> 38.0Improved
add balanced feature pyramid (BFP) to the baseline (ablation)FSAF · COCO val2017AP: 35.9 -> 36.8Improved
add SW and SS training strategy on top of BFP (ablation)FSAF + BFP · COCO val2017AP: 36.8 -> 38.8Improved
vary eta of generalized centerness from 1.0 to 2.0 (ablation)SW · COCO val2017AP: 37.0 -> 36.6Hurt
vary top-k selected levels from 2 to 5 (ablation)SAPD soft selection · COCO val2017AP: 37.9 -> 38.0 -> 37.9 -> 37.9No clear effect
train feature selection network jointly but do not use its weights (ablation)FSAF + SW · COCO val2017AP: 37.0 -> 37.1No clear effect
replace test-time center-ness (cls) with training-time soft weighting (ablation)FSAF · COCO val2017AP: 36.1 -> 37.0Improved
add center-ness on regression branch on top of soft weighting (ablation)FSAF + SW · COCO val2017AP: 37.0 -> 36.8No clear effect
apply soft weighting to classification loss only (ablation)FSAF · COCO val2017AP: 35.9 -> 33.3Hurt
apply soft weighting to localization loss only (ablation)FSAF · COCO val2017AP: 35.9 -> 35.6Hurt

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