AI Paper Atlas

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

GeoCoBox: Box-supervised 3D Tumor Segmentation via Geometric Co-embedding

Tianzhong Lan, Zhang Yi, Xiuyuan Xu, Min Zhu

AAAI 2026 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic 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
use soft margin + Dice loss for AD-CAM instead of SCE + BCE (ablation)GeoCoBox AD-CAM · LIDC-IDRIDSC (%): 68.25 -> 76.09Improved
replace BCE with Dice loss in AD-CAM (keeping SCE) (ablation)GeoCoBox AD-CAM · LIDC-IDRIDSC (%): 68.25 -> 73.92Improved
use GCL refining scale tau=8 rather than 4 (ablation)GeoCoBox GCL · LIDC-IDRIDSC (%): 73.21 -> 76.09Improved
use GCL refining scale tau=8 rather than 16 (ablation)GeoCoBox GCL · LIDC-IDRIDSC (%): 74.32 -> 76.09Improved
use intensity range delta=20HU rather than 10HU or 40HU (ablation)GeoCoBox GCL · LIDC-IDRIDSC (%): 72.89 / 75.22 -> 76.09Improved
use cosine similarity instead of SSIM or MSE (ablation)GeoCoBox GCL · LIDC-IDRIDSC (%): 74.10 (SSIM) / 75.60 (MSE) -> 76.09Improved
add AD-CAM and GCL components to Vanilla baseline (ablation)GeoCoBox · LIDC-IDRIDSC and HD95Improved
replace 3D UNet backbone with 3D UNETRGeoCoBox · MSD-PancreasHD95Mixed
train on LIDC-IDRI and test on MSD-Lung (cross-dataset)GeoCoBox · MSD-LungDSC (%): 50.99 -> 54.87Improved
restrict contrastive refinement to center and boundary pointsGeoCoBox GCL · parameter count versus GPCSparametersImproved

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