AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training

Yuting He, Guanyu Yang, Rongjun Ge, Yang Chen, Jean-Louis Coatrieux, Boyu Wang, Shuo Li

CVPR 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Pretext-task visual pre-training · 51 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
Use GVSL instead of the strongest listed baseline3D U-Net pre-training · SHC linearDSC%: 56.1 -> 68.4Improved
Use GVSL instead of the strongest listed baseline3D U-Net pre-training · SAC linearDSC%: 22.5 -> 28.7Improved
Use GVSL instead of the strongest listed baseline3D U-Net pre-training · CCC linearAUC%: 62.1 -> 60.8Hurt
Use GVSL instead of the strongest listed baseline3D U-Net pre-training · SBM linearDSC%: 67.5 -> 79.9Improved
Remove Z-Matching (ablation)GVSL · SHC linearDSC%: 68.4 -> 49.1Hurt
Remove self-restoration warm-up (ablation)GVSL · SAC linearDSC%: 28.7 -> 0.0Hurt
Remove affine matching (ablation)GVSL · CCC fine-tuningAUC%: 82.2 -> 79.8Hurt
Remove affine matching (ablation)GVSL · SAC fine-tuningDSC%: 81.3 -> 82.3Improved

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