AI Paper Atlas

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

P2Object: Single Point Supervised Object Detection and Instance Segmentation

Pengfei Chen, Xuehui Yu, Xumeng Han, Kuiran Wang, Guorong Li, Lingxi Xie, Zhenjun Han, Jianbin Jiao

IJCV 2025 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 4 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 PBR stage losses (L_mil2 and L_neg) to CBP (ablation)P2BNet · COCO-17 valAP: 13.7 -> 21.7Improved
add negative loss L_neg on top of L_mil2 (ablation)P2BNet · COCO-17 valAP: 12.7 -> 21.7Improved
add L_mil2 in PBR without negative loss (ablation)P2BNet · COCO-17 valAP: 13.7 -> 12.7Hurt
use MIL loss L_mil1 instead of treating all bag proposals as positive (ablation)P2BNet CBP · COCO-17 valAP: 2.9 -> 13.7Improved
optimize PBR jointly with CBP (ablation)P2BNet · COCO-17 trainmIoU_box: 50.2 -> 52.5Improved
replace basic sampling with SPSD sampling in the last PBR stage (P2BNet++) (ablation)P2BNet-FR · COCO-17 valAP: 22.1 -> 23.1Improved
add P2MNet (object-aware pixel perception with BSP) on P2BNet++ (ablation)P2BNet++-FR · COCO-17 valAP: 23.1 -> 25.9Improved
add P2MNet pixel perception for segmentation vs BoxInst on P2BNet++ pseudo boxes (ablation)P2BNet++-BoxInst · COCO-17 val (segmentation)AP: 21.0 -> 23.1Improved
retrain with Sparse R-CNN instead of Faster R-CNNP2MNet · COCO-17 valAP: 25.9 -> 29.6Improved
use COCO-pretrained detector instead of ImageNetP2MNet-FR · Cityscapes valAP: 25.0 -> 27.4Improved
upgrade P2BNet to P2BNet++ then P2MNet (ablation)P2Object detector · VOC 2007 testAP50: 60.4 -> 66.2 -> 68.2Improved
use P2MNet-MR instead of SAM-generated pseudo masksMask R-CNN · COCO-17 val (segmentation)AP: 20.9 -> 23.1Improved

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