NEARL-CLIP reports top accuracy on three medical image classification benchmarks by adding bidirectional cross-modal attention and orthogonalized adapters to CLIP with only 1.46M parameters.
V oco: A simple-yet-effective volume contrastive learning framework for 3d medical image analysis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
NEARL: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
NEARL-CLIP reports top accuracy on three medical image classification benchmarks by adding bidirectional cross-modal attention and orthogonalized adapters to CLIP with only 1.46M parameters.