AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Cyto-SSL: A Self-Supervised Pretraining Framework for Cytology Foundation Model

Yiming Zhang, Rui Yan, Xiaohua Wan, Yifan Zhao, Shuang Feng, Zhetao Xu, Ying Wang, Fa Zhang, Bin Hu

AAAI 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Data-efficient and robust self-supervision · 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 Nuclei-Centered Perturbation to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (ABMIL)accuracy (%): 91.77 -> 93.07Improved
add Nuclei-Centered Perturbation to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (LESS)accuracy (%): 92.20 -> 93.50Improved
add sparse self-attention to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (ABMIL)accuracy (%): 91.77 -> 93.51Improved
add sparse self-attention to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (LESS)AUC: 0.963 -> 0.952Mixed
add iRPE to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (ABMIL)accuracy (%): 91.77 -> 92.21Improved
add iRPE to DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (LESS)accuracy (%): 92.20 -> 93.07Improved
combine all three components (full Cyto-SSL) versus DINO (ablation)DINO ViT-tiny · Cervical Cytologic WSI (LESS)accuracy (%): 92.20 -> 95.67Improved
add Cyto-SSL to DINODINO ViT-tiny · Cervical Cytologic WSI (ABMIL)accuracy (%): 91.77 -> 94.37Improved
add Cyto-SSL to SimCLRSimCLR ViT-tiny · Cervical Cytologic WSIAUC: 0.932 -> 0.915Mixed
add Cyto-SSL to MoCoMoCo ViT-tiny · Cervical Cytologic WSIaccuracy (%): 87.88 -> 88.74Improved
pretrain from scratch on cytology instead of ImageNet ResNet-50 featuresABMIL · Cervical Cytologic WSIaccuracy (%): 83.04 -> 94.37Improved
pretrain from scratch with Cyto-SSL instead of LoRA-tuned Prov-GigaPathABMIL · Cervical Cytologic WSIaccuracy (%): 92.50 -> 94.37Improved

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