AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology

Basit Alawode, Moshira Abdalla, Dwarikanath Mahapatra, Muhammad Muzammal Naseer, Sajid Javed

ECCV 2026 · Architectures and efficiency › Attention and transformers · approach: Token merging and masked pretraining · 0 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 multi-resolution inputs by concatenation (ablation)HIPT-style hierarchy · PANDAbalanced accuracy: 0.704 -> 0.762Improved
add CCRA module (ablation)MRPT · PANDAbalanced accuracy: 0.762 -> 0.823Improved
add ACT and [CLS] concat token fusion (ablation)MRPT · PANDAbalanced accuracy: 0.823 -> 0.848Improved
add 3-stage hierarchical SSL (ablation)MRPT · PANDAbalanced accuracy: 0.848 -> 0.866Improved
use consecutive CCRA instead of distant pairing 10x-40x (ablation)MRPT · PANDAbalanced accuracy: 0.824 -> 0.866Improved
use all three resolutions instead of 10x+20x (ablation)MRPT · PANDAbalanced accuracy: 0.852 -> 0.866Improved
use CCRA instead of averaged [CLS] token fusion (ablation)MRPT · PANDAbalanced accuracy: 0.848 -> 0.862Improved
use CCRA instead of all-token attention (ablation)MRPT · PANDAbalanced accuracy: 0.850 -> 0.862Improved
increase ViT10x embedding size to 768 (ablation)MRPT · PANDAbalanced accuracy: 0.866 -> 0.846No clear effect
increase CCRA layers K to 2 (ablation)MRPT · PANDAbalanced accuracy: 0.866 -> 0.843No clear effect
train and test on synthetic pyramid from 20x only (ablation)MRPT · PANDAbalanced accuracy: 0.866 -> 0.723Hurt
replace HIPT with MRPT under matched dataMRPT · Camelyon17F1: 0.782 -> 0.883Improved

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