AI Paper Atlas

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

Graph-Constrained Contrastive Regularization for Semi-Weakly Volumetric Segmentation

Simon Reiß, Constantin Seibold, Alexander Freytag, Erik Rodner, Rainer Stiefelhagen

ECCV 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Semi-supervised medical segmentation

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
use Con2R regularization instead of best competing semi-supervised method3D UNet · RETOUCH M(24)mIoU: 48.2 vs 46.2 (FixMatch)Improved
add Con2R to 3D UNet3D UNet · RETOUCH M(3)mIoU: 12.0 -> 14.8Improved
add Con2R to 3D UNet3D UNet · RETOUCH M(12)mIoU: 31.1 -> 38.6Improved
add Con2R to 3D UNet3D UNet · RETOUCH M(24)mIoU: 43.8 -> 48.2Improved
add Con2R when all volumes are fully annotated3D UNet · RETOUCH M(full)mIoU: 54.9 -> 54.6No clear effect
add Con2R to 3D UNet3D UNet · BraTS M(24)mIoU (average): 38.8 -> 43.2Improved
use 16x16x16 receptive volume instead of 32x32x32 (ablation)Con2R · RETOUCH M(24) validationvalidation mIoU: 47.1 -> 49.1Improved
use 16x16x16 receptive volume instead of 160x160x160 (ablation)Con2R · RETOUCH M(24) validationvalidation mIoU: 46.5 -> 49.1Improved
increase number of sampled graph vertices from 216 to 1728 (ablation)Con2R · RETOUCH M(24) validationvalidation mIoU: 46.9 -> 49.1Improved
increase number of sampled graph vertices from 1000 to 1728 (ablation)Con2R · RETOUCH M(24) validationvalidation mIoU: 47.8 -> 49.1Improved
mix positional and semantic constraints with alpha 0.2 rather than only one (ablation)Con2R · RETOUCH M(24) validationvalidation mIoUImproved
use Con2R vs 3D UNet on SRF class3D UNet · RETOUCH M(24) SRFIoU: 73.0 -> 79.1Improved

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