AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

Pengfei Chen, Xuehui Yu, Xumeng Han, Najmul Hassan, Kai Wang, Jiachen Li, Jian Zhao, Humphrey Shi, Zhenjun Han, Qixiang Ye

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 81 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 negative sampling and negative loss L_neg in PBR (ablation)P2BNet · COCO-17 valAP: 12.7 -> 21.7Improved
add one PBR refinement stage after CBP (ablation)P2BNet · COCO-17 valAP: 13.7 -> 21.7Improved
use two PBR iterations instead of one (ablation)P2BNet · COCO-17 valAP: 21.7 -> 21.9No clear effect
use three PBR iterations instead of one (ablation)P2BNet · COCO-17 valAP: 21.7 -> 21.3Hurt
add center jitter to PBR proposals (ablation)P2BNet · COCO-17 valAP: 14.2 -> 21.7Improved
use balanced proposal sampling per object (ablation)P2BNet · COCO-17 valAP: 12.9 -> 21.7Improved
use L_mil1 instead of treating all bag proposals as positive (L_pos) (ablation)P2BNet CBP · COCO-17 valAP: 2.9 -> 13.7Improved
add L_pseudo using CBP pseudo boxes as positives (ablation)P2BNet · COCO-17 valAP: 21.7 -> 18.5Hurt
merge boxes with bag score instead of classification score (ablation)P2BNet · COCO-17 valAP: 17.4 -> 21.7Improved
increase top-k from 1 to 4 in box merging (ablation)P2BNet · COCO-17 valAP: 12.2 -> 22.1Improved
use ResNet-101 instead of ResNet-50 backbone in P2BNet (ablation)P2BNet · COCO-17 valAP: 21.7 -> 20.8Hurt
replace OTSP-based UFO2 with P2BNet-FR (QC points)P2BNet-FR · COCO-17 valAP50: 28.9 -> 47.3Improved

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