AI Paper Atlas

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

Object Localization Under Single Coarse Point Supervision

Xuehui Yu, Pengfei Chen, Di Wu, Najmul Hassan, Guorong Li, Junchi Yan, Humphrey Shi, Qixiang Ye, Zhenjun Han

CVPR 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 39 citations (OpenAlex)

Check 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
refine coarse points with CPR before P2PNet localizationP2PNet · COCO, DOTA, SeaPersonmAP^all_1.0: 38.48 -> 55.46; 48.34 -> 63.81; 76.52 -> 85.86Improved
add MIL loss to annotation and negative losses (ablation)CPR + P2PNet · COCOmAP^all_1.0: 51.82 -> 55.46Improved
replace MIL loss with positive-point loss (ablation)CPR + P2PNet · COCOmAP^all_1.0: 55.46 -> 42.72Hurt
add annotation loss to MIL and negative losses (ablation)CPR + P2PNet · COCOmAP^all_1.0: 54.24 -> 55.46Improved
add negative loss to MIL and annotation losses (ablation)CPR + P2PNet · COCOmAP^all_1.0: 39.45 -> 55.46Improved
use P3 sampling radius R=8 rather than R=5 (ablation)CPR · COCOmAP^all_1.0: 53.32 -> 55.46Improved
increase P3 sampling radius from R=8 to R=25 (ablation)CPR · COCOmAP^all_1.0: 55.46 -> 53.85Hurt
retain all three point-refinement constraints (ablation)CPR · COCOmAP^all_1.0: 54.25 -> 55.46; 52.69 -> 55.46Improved
use coarse point annotations with CPR instead of coarse points without CPR (ablation)P2PNet · COCOmAP^all_1.0: 38.48 -> 55.46Improved
use coarse points with CPR rather than center-point annotations (ablation)P2PNet · COCOmAP^all_1.0: 55.46 -> 57.47Hurt
use ResNet-101 instead of ResNet-50 for CPRNet and P2PNet (ablation)CPR + P2PNet · COCOmAP^all_1.0: 55.46 -> 56.43Improved
replace circular point sampling with rectangular sampling (ablation)CPR · COCOmAP^all_1.0: 55.46 -> 55.39No clear effect

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