Search papers, labs, and topics across Lattice.
4
0
5
0
CytoFormer achieves 85% accuracy in cell classification while dramatically reducing the need for extensive manual annotations, revolutionizing histopathological analysis.
Refining low-confidence pseudo-labels with diffusion techniques boosts histopathology segmentation accuracy by over 6% compared to traditional methods.
ProBAG achieves superior segmentation accuracy by combining visual and text prototypes, significantly improving weakly supervised histopathology segmentation without relying on external models.
Re-ranking control alone boosts key performance metrics by over 2%, but extending it to fine ranking unlocks even greater gains without sacrificing system stability.