New paper extends 2D CLIP-based cell microscopy anomaly detection to 3D morphology with text contrastive learning
A new arXiv paper presents 3D cell morphology–clinical text contrastive learning using a Voxel Swin Transformer and finding-encoder domain adaptation, building on prior 2D CLIP dual-encoder work with LoRA that reached anomaly-scoring ROC-AUC up to 0.985.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv cs.CV
3D Cell Morphology--Clinical Text Contrastive Learning with Voxel Swin Transformer and Finding Encoder Domain-Adaptation