COBRA trains a Mamba-2-based slide encoder with contrastive learning across multiple foundation models and magnifications, beating prior slide encoders by +4.4% average AUC on CPTAC with only 3,048 TCGA pretraining slides.
Chen, Chengkuan Chen, Yicong Li, Tiffany Y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning
COBRA trains a Mamba-2-based slide encoder with contrastive learning across multiple foundation models and magnifications, beating prior slide encoders by +4.4% average AUC on CPTAC with only 3,048 TCGA pretraining slides.