Dictionary learning with ICFL and control-data whitening extracts sparse features from microscopy foundation models that correlate with cell types and genetic perturbations.
As observed, the null space component consistently yields the same probing accuracy as the entire token, while the row space component yields significantly lower accuracy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Dictionary learning with ICFL and control-data whitening extracts sparse features from microscopy foundation models that correlate with cell types and genetic perturbations.