AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

MuViT: Multi-Resolution Vision Transformers for Learning Across Scales in Microscopy

Albert Dominguez Mantes, Gioele La Manno, Martin Weigert

CVPR 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
use true world-coordinate bounding boxes instead of naive centered ones (ablation)MuViT[1,4]+UNETR · SYNTHETICmDSC: 0.3864 -> 0.9538Improved
add coarser resolution level (1 -> 1,4) (ablation)MuViT+UNETR · SYNTHETICmDSC: 0.5003 -> 0.9538Improved
add resolution levels 8 and 32 to single-level encoder (ablation)MuViT+Mask2Former · MOUSE (256x256 input)mDSC: 0.391 -> 0.901Improved
use true world coordinates instead of naive (ablation)MuViT[1,8,32]+Mask2Former · MOUSEmDSC: 0.820 -> 0.901Improved
use true world coordinates instead of naive (ablation)MuViT[1,8,32]+UNETR · MOUSEmDSC: 0.793 -> 0.883Improved
add coarser level 8 to single-level encoder (ablation)MuViT+UNETR · KPISDSC: 0.8492 -> 0.8958Improved
add coarser level 8 to single-level encoder (ablation)MuViT+Mask2Former · KPISDSC: 0.8390 -> 0.8866Improved
add more resolution levels to the MAE encoder (1 -> 1,8 -> 1,8,32,64) (ablation)MuViT-MAE frozen features · KPIS linear probingOvA ROC-AUC: 0.958 -> 0.963 -> 0.988Improved
use true world coordinates instead of naive in MAE (ablation)MuViT[1,8,32] MAE · MOUSE reconstructionreconstruction MSE: level 8: 1.589 × 10−2 (naive) vs 2.274 × 10−2; level 32: 1.373 × 10−2 vs 1.464 × 10−2Mixed
use true world coordinates instead of naive in MAE (ablation)MuViT[1,8,32,64] MAE · KPIS reconstructionreconstruction MSE: level 64: 7.302 × 10−3 -> 6.913 × 10−3Improved
MAE pretraining of multi-resolution encoderMuViT[1,8,32]+Mask2Former · MOUSE fine-tuningvalidation mDSC: 0.843 after 10 epochs, above 0.88 by epoch 25Improved
increase input size for DeepLabV3 baseline from 256 to 1024 (ablation)DeepLabV3 · MOUSEmDSC: 0.520 -> 0.676 -> 0.843Improved

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