AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling

Yaxiong Chen, Qicong Wang, Chunlei Li, Jingliang Hu, Yilei Shi, Shengwu Xiong, Xiao Xiang Zhu, Lichao Mou

AAAI 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation · 1 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 task prompts via prompting-upon-decoding (ablation)ProPL · 1/16 labeledmDice: 61.54 -> 81.13Improved
add task prompts via prompting-upon-decoding (ablation)ProPL · 1/8 labeledmDice: 63.19 -> 83.35Improved
add task prompts via prompting-upon-decoding (ablation)ProPL · 1/4 labeledmDice: 64.67 -> 85.50Improved
add UPLC pseudo-label calibration (ablation)ProPL · 1/16 labeledmDice: 78.63 -> 81.13Improved
add UPLC pseudo-label calibration (ablation)ProPL · 1/16 labeledmIoU: 68.56 -> 71.96Improved
add UPLC pseudo-label calibration (ablation)ProPL · 1/8 labeledmDice: 81.20 -> 83.35Improved
add UPLC pseudo-label calibration (ablation)ProPL · 1/4 labeledmDice: 83.84 -> 85.50Improved
add UPLC without task prompts (ablation)ProPL w/o PuD · 1/16 labeledmDice: 60.17 -> 61.54No clear effect
use two stochastic perturbations instead of other counts (ablation)UPLC · 1/4 labeledmDice: 85.61Improved
use dropout instead of Gaussian noise for perturbation (ablation)UPLC · ultrasoundmIoU: 2.58 mIoU drop with Gaussian noiseImproved
increase number of perturbations N by 1 (ablation)UPLC · ultrasoundcost: +2.43 GB memory, +27.6 s per epochHurt
use prompting-upon-decoding instead of CLIP-UM prompting (ablation)ProPL · ultrasoundmDice: +3.05%Improved

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