AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

Lingyu Chen, Yawen Zeng, Yue Wang, Peng Wan, Guochen Ning, Hongen Liao, Daoqiang Zhang, Fang Chen

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Cross-domain translation and pose · 2 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
remove both shared experts (STE and SEE) (ablation)COME · inter-organ integrationmean AP: 0.5819 -> 0.6587 when added (-7.68% mean AP)Improved
add clustering before routing (ablation)COME · inter-organ integrationmean AP: 0.6264 -> 0.6587Improved
add source-specific traceability loss (ablation)COME · inter-organ integrationmean AP: 0.6320 -> 0.6587Improved
train on integrated inter-organ data instead of single datasetDINO · 8 US datasetsmean AP: 0.6125 (single) -> 0.5792 (inter-organ)Hurt
use COME instead of DINO under joint trainingUS lesion detection · inter-organ integrationmean AP: 0.5792 -> 0.6587Improved
set the number of experts to 8 (equal to number of sources) (ablation)COME · inter-organ integrationmean AP: 4 experts 0.6416, 10 experts 0.6459 -> 8 experts 0.6565Improved
use Top-K of 3 instead of 4 (ablation)COME router · inter-organ integrationmean AP: 0.6333 -> 0.6587Improved
train on BUSI and test on other breast datasetsCOME vs DINO · BUSC zero-shotAP: 0.043 -> 0.297Improved
combine both clustering strategies (Mixing) (ablation)COME · inter-organ integrationmean AP and inference time: 0.6587 -> 0.6337; 132 -> 845 usHurt
use Fine2Coarse instead of Multi-Step clustering (ablation)COME · inter-organ integrationinference time: 615 -> 132 us with comparable mean APImproved

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