AI Paper Atlas

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

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

Teng Zhang, Ziqian Fan, Mingxin Liu, Xin Zhang, Xudong Lu, Wentong Li, Yue Zhou, Yi Yu, Xiang Li, Junchi Yan, Xue Yang

ICLR 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection

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 Progressive Label Assignment (multi-level FPN assignment from pseudo labels) (ablation)Point2RBox-v2 · DOTA-v1.0 end-to-endAP50: 51.0 -> 56.6Improved
add PLA (ablation)Point2RBox-v2 · DOTA-v1.0 two-stageAP50: 62.6 -> 64.6Improved
add Prior-Guided Dynamic Mask Loss (SAM + watershed routing) (ablation)Point2RBox-v2 · DOTA-v1.0 end-to-endAP50: 51.0 -> 54.2Improved
combine PLA and PGDM-Loss (ablation)Point2RBox-v2 · DOTA-v1.0 end-to-endAP50: 51.0 -> 59.6Improved
switch PLA from watershed boxes to network predictions mid-training (epoch 3-6) instead of at epoch 0 (ablation)PLA · DOTA-v1.0 end-to-endAP50: 56.6 -> 59.6Improved
use only watershed boxes for the whole training (switch epoch 12) (ablation)PLA · DOTA-v1.0 end-to-endAP50: 59.6 -> 56.3Hurt
route all instances to SAM (N_thr infinity) instead of only sparse scenes (ablation)PGDM-Loss · DOTA-v1.0 end-to-endAP50: 59.6 -> 57.2Hurt
increase sparse-scene threshold N_thr from 4 to 8 (ablation)PGDM-Loss · DOTA-v1.0 end-to-endAP50: 59.6 -> 58.9No clear effect
use prior-guided mask selection instead of SAM native confidence (ablation)PGDM-Loss · DOTA-v1.0 end-to-endAP50: 57.86 -> 59.61Improved
use prior-guided mask selection instead of SAM native confidence (ablation)PGDM-Loss · DOTA-v1.0 two-stageAP50: 63.59 -> 66.09Improved
add PLA and PGDM to PWOOD with 10% point labelsPWOOD · DOTA-v1.0AP50: 42.35 -> 50.67Improved
add PLA and PGDM to PWOOD with 10% point labelsPWOOD · DOTA-v1.5AP50: 35.33 -> 43.25Improved

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