AI Paper Atlas

Research map / Detection and segmentation / CNN features

Dive Deeper Into Box for Object Detection

Ran Chen, Yong Liu, Mengdan Zhang, Shu Liu, Bei Yu, Yu-Wing Tai

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 17 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 box decomposition and recombination (D&R) (ablation)FCOS baseline · COCO minival (ResNet-50)AP: 33.6 -> 34.8Improved
add D&R (ablation)FCOS baseline · COCO minival (ResNet-50)AP75: 35.0 -> 36.4Improved
add semantic consistency module (ablation)FCOS baseline · COCO minival (ResNet-50)AP: 33.6 -> 37.2Improved
add semantic consistency module on top of D&R (ablation)Baseline + D&R · COCO minival (ResNet-50)AP: 34.8 -> 38.0Improved
add D&R on top of semantic consistency (ablation)Baseline + Consistency · COCO minival (ResNet-50)AP: 37.2 -> 38.0Improved
add both modules (ablation)FCOS baseline · COCO minival (ResNet-50)AP_L: 43.7 -> 50.4Improved
replace predefined center sampling (PN) with adaptive consistency filtering (ablation)FCOS baseline · COCO minival (positive assignment, ResNet-50)AP: 34.2 -> 35.3Improved
add center sampling (PN) (ablation)FCOS baseline · COCO minival (positive assignment, ResNet-50)AP: 33.6 -> 34.2Improved
add ignore regions between positive and negative (PNI) (ablation)FCOS baseline · COCO minival (positive assignment, ResNet-50)AP: 33.6 -> 33.7No clear effect
add adaptive mean-threshold selection instead of constant ratio c=0.7 (ablation)semantic consistency filtering · COCO minival (sampling ratio, ResNet-50)AP: 35.1 -> 35.3Improved
vary constant sampling ratio c from 0.4 to 0.7 (ablation)semantic consistency filtering · COCO minival (sampling ratio, ResNet-50)AP: 34.6 -> 34.1 -> 34.7 -> 35.1Mixed
add D&R to IoU loss (ablation)FCOS box regression · COCO trainval35k training IoUmean IoU of boxes: 0.34 -> 0.47Improved

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