Random unbalanced batch sampling outperforms explicit class balancing for zero-shot learning in a reproduced 3D CT image-text model, with sub-linear gains from more data.
Contrastive learning of medical visual representations from paired images and text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CLIP Architecture for Abdominal CT Image-Text Alignment and Zero-Shot Learning: Investigating Batch Composition and Data Scaling
Random unbalanced batch sampling outperforms explicit class balancing for zero-shot learning in a reproduced 3D CT image-text model, with sub-linear gains from more data.