AI Paper Atlas

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

Self-supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation

Cheng Ouyang, Carlo Biffi, Chen Chen, Turkay Kart, Huaqi Qiu, Daniel Rueckert

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 302 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 superpixel self-supervised training (no annotations) to PANet (ablation)PANet · Abd-CT setting 2mean Dice: 29.43 -> 44.42Improved
add superpixel self-supervised training to PANet (ablation)PANet · Abd-MRI setting 2mean Dice: 46.33 -> 54.85Improved
add adaptive local prototype pooling to SSL-PANet (ablation)SSL-PANet · Abd-CT setting 2mean Dice: 44.42 -> 63.02Improved
add adaptive local prototype pooling to SSL-PANet (ablation)SSL-PANet · Abd-MRI setting 2mean Dice: 54.85 -> 73.02Improved
add adaptive local prototype pooling to supervised PANet (ablation)PANet · Card-MRI setting 1mean Dice: 42.96 -> 60.34Improved
add superpixel SSL to ALPNet (ablation)ALPNet · Card-MRI setting 1mean Dice: 60.34 -> 76.90Improved
add SSL to ALPNet instead of supervised training (ablation)ALPNet · Abd-CT setting 1mean Dice: 41.63 -> 73.35Improved
add intensity and geometric transforms between support and query (ablation)SSL-ALPNet · Abd-CT setting 2mean Dice: 55.13 -> 63.02Improved
add intensity transform on top of geometric transform (ablation)SSL-ALPNet · Abd-CT setting 2 liverDice: 78.93 -> 73.65Hurt
raise minimum pseudolabel size from 400 to 1600 px (ablation)SSL-ALPNet · Abd-CT setting 2mean Dice: 63.02 -> 57.08Hurt
lower minimum pseudolabel size from 400 to 100 px (ablation)SSL-ALPNet · Abd-CT setting 2mean Dice: 63.02 -> 55.49Hurt
initialize with COCO weights only, without training (ablation)ALPNet-init · Abd-CT setting 2mean Dice: 20.90 vs 63.02 for SSL-ALPNetHurt

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