A DINO-style SSL method with a segmentation teacher and stability-weighted HDBSCAN contrastive loss improves hierarchical morphology-aware single-cell embeddings over strong baselines.
Title resolution pending
1 Pith paper cite this work, alongside 37 external citations. Polarity classification is still indexing.
1
Pith paper citing it
37
external citations · external index
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HASSL: Hierarchy-Aware Self-Supervised Learning Framework for Single Cell Microscopy
A DINO-style SSL method with a segmentation teacher and stability-weighted HDBSCAN contrastive loss improves hierarchical morphology-aware single-cell embeddings over strong baselines.