AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Homeomorphism Prior for False Positive and Negative Problem in Medical Image Dense Contrastive Representation Learning

Yuting He, Boyu Wang, Rongjun Ge, Yang Chen, Guanyu Yang, Shuo Li

TPAMI 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 9 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 GEMINI dense contrastive pre-learning to a U-Net trained with five labelsU-Net · FS-Semi averageDSC: 79.1 -> 88.7Improved
replace GVSL-Semi with GEMINI-Semi (add GSS, smooth, bijection)GVSL-Semi · FS-Semi averageDSC: 86.2 -> 88.7Improved
add GEMINI to a TransUNet backboneTransUNet · FS-Semi averageDSC: 72.8 -> 87.9Improved
add GEMINI to a SwinUNet backboneSwinUNet · FS-Semi averageDSC: 57.5 -> 84.9Improved
add GEMINI-MIP pre-training instead of random initialization2D U-Net · SS-MIP averageDSC: 73.6 -> 87.0Improved
add GSS and smoothness on top of GVSL-MIPGVSL-MIP · SS-MIP averageDSC: 86.1 -> 87.0Improved
add the geometric visual similarity (GVS) alone for correspondence learning (ablation)GEMINI-Semi · T3 2D chest structuresDSCHurt
add the geometric semantic similarity (GSS) to GVS (ablation)GEMINI-Semi · T1 and T3DSCImproved
add smoothness loss for continuity (ablation)GEMINI-Semi · T1 and T3DSCImproved
add the bijection (inverse mapping) loss (ablation)GEMINI-Semi · T1 and T3DSCImproved
enlarge the Deformer receptive field r (ablation)GEMINI-Semi · T1 3D cardiacDSC: around 90% DSCNo clear effect
add the DHL deformer module (soft learning of feature pairs) (ablation)GEMINI-Semi · T1 3D cardiacDSC: more than 5% DSCImproved

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