AI Paper Atlas

Research map / Detection and segmentation / CNN features

Side-Aware Boundary Localization for More Precise Object Detection

Jiaqi Wang, Wenwei Zhang, Yuhang Cao, Kai Chen, Jiangmiao Pang, Tao Gong, Jianping Shi, Chen Change Loy, Dahua Lin

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 190 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 SABL to RetinaNetRetinaNet R-101 · COCO test-devAP: 1.7%Improved
add SABL to Faster R-CNNFaster R-CNN R-101 · COCOAP: 3.0%Improved
add SABL to Cascade R-CNNCascade R-CNN R-101 · COCO test-devAP: 0.9%Improved
use boundary regression targets instead of bounding box regression (ablation)Faster R-CNN R-50 · COCO valAP: 36.4 -> 37.3Improved
add side-aware feature extraction (SAFE) (ablation)Faster R-CNN R-50 with boundary regression · COCO valAP: 37.3 -> 38.5Improved
use heavier 4conv1fc head instead of SAFE (ablation)Faster R-CNN with boundary regression · COCO valAP: 37.3 -> 37.4No clear effect
replace bounding box regression with BLB (ablation)Faster R-CNN R-50 · COCO valAP: 36.4 -> 38.3Improved
add BLB to SAFE (ablation)Faster R-CNN R-50 · COCO valAP: 38.5 -> 39.0Improved
add bucketing-guided rescoring (BGR) (ablation)SABL · COCO valAP: 39.0 -> 39.7Improved
bucketing without fine regression (ablation)Faster R-CNN R-50 · COCO valAP: 36.4 -> 32.8Hurt
localize object center with bucketing instead of boundaries (CLB vs BLB) (ablation)Faster R-CNN R-50 · COCO valAP: 38.3 -> 36.9Hurt
attention mask instead of max pooling for aggregating RoI features (ablation)SAFE · COCO valAP: 39.4 -> 39.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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