AI Paper Atlas

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

Cello: A Universal Cell-wise Feature Aggregation framework for Reliable Pathology Images Analysis

Hengrui Lou, Weihan Li, Jiazhen Yang, Lingxiang Jia, Shengxuming Zhang, Linyun Zhou, Xiuming Zhang, Zhenyang Wang, Mingli Song, Zunlei Feng

ICML 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors

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 cell-wise feature learning and alignment (A1) (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.799 -> 0.832Improved
add class-level alignment (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.801 -> 0.832Improved
add token-level alignment (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.829 -> 0.832No clear effect
add dimension mapping (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.825 -> 0.832Improved
add local prototype contrast (B2) (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.801 -> 0.832Improved
use several prototypes per class instead of s = 1 (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.830 -> 0.832No clear effect
add decision-route reliable learning (B3) (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.812 -> 0.832Improved
add local-global route calibration (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.815 -> 0.832Improved
add cell-local refinement (ablation)Cello · CPTAC-CCRCC gradingAUC: 0.824 -> 0.832Improved
add cell-wise aggregation over patch-only encoding (ablation)Cello · CPTAC-CCRCC diagnosisAUC: 0.834 -> 0.857Improved
use Cello instead of best PFM baselineCHIEF · 4500PCas gradingAUC: +6.0Improved
use Cello instead of best PFM baselineCHIEF · TCGA-CRC diagnosisAUC: +4.6Improved

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